{"data":[{"id":"gpt-6.1-terra-pro","name":"OpenAI: GPT-6.1 Terra Pro","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra-pro:batch","name":"OpenAI: GPT-6.1 Terra Pro (batch)","created":1793038556,"description":"GPT-6.1 Terra Pro is the same underlying model as [GPT-6.1 Terra](https://openrouter.ai/openai/gpt-6.1-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":9.375000000000001e-7,"max_prompt_cost":0.7875,"max_completion_cost":0.4800000000000001,"max_cost":1.1715},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0011778969984043424,"max_prompt_cost":989.4334786596473,"max_completion_cost":603.0832631830233,"max_cost":1471.900089206066},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-terra-pro-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra","name":"OpenAI: GPT-6.1 Terra","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-terra:batch","name":"OpenAI: GPT-6.1 Terra (batch)","created":1793038409,"description":"GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screenshots...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":9.375000000000001e-7,"max_prompt_cost":0.7875,"max_completion_cost":0.4800000000000001,"max_cost":1.1715},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0011778969984043424,"max_prompt_cost":989.4334786596473,"max_completion_cost":603.0832631830233,"max_cost":1471.900089206066},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-terra-20261026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol-pro","name":"OpenAI: GPT-6.1 Sol Pro","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol-pro:batch","name":"OpenAI: GPT-6.1 Sol Pro (batch)","created":1790702886,"description":"GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-sol-pro-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol","name":"OpenAI: GPT-6.1 Sol","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6.1-sol:batch","name":"OpenAI: GPT-6.1 Sol (batch)","created":1790702882,"description":"GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6.1-sol-20260929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna-pro","name":"OpenAI: GPT-6 Luna Pro","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.875e-7,"max_prompt_cost":0.1575,"max_completion_cost":0.096,"max_cost":0.2343},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00023557939968086843,"max_prompt_cost":197.88669573192948,"max_completion_cost":120.61665263660464,"max_cost":294.3800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna-pro:batch","name":"OpenAI: GPT-6 Luna Pro (batch)","created":1790100791,"description":"GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":9.375e-8,"max_prompt_cost":0.07875,"max_completion_cost":0.048,"max_cost":0.11715},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.00011778969984043421,"max_prompt_cost":98.94334786596474,"max_completion_cost":60.30832631830232,"max_cost":147.1900089206066},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-luna-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna","name":"OpenAI: GPT-6 Luna","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.875e-7,"max_prompt_cost":0.1575,"max_completion_cost":0.096,"max_cost":0.2343},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00023557939968086843,"max_prompt_cost":197.88669573192948,"max_completion_cost":120.61665263660464,"max_cost":294.3800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-luna:batch","name":"OpenAI: GPT-6 Luna (batch)","created":1790100786,"description":"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":9.375e-8,"max_prompt_cost":0.07875,"max_completion_cost":0.048,"max_cost":0.11715},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.00011778969984043421,"max_prompt_cost":98.94334786596474,"max_completion_cost":60.30832631830232,"max_cost":147.1900089206066},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-luna-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol-pro","name":"OpenAI: GPT-6 Sol Pro","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol-pro:batch","name":"OpenAI: GPT-6 Sol Pro (batch)","created":1790100781,"description":"GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-sol-pro-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol","name":"OpenAI: GPT-6 Sol","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-sol:batch","name":"OpenAI: GPT-6 Sol (batch)","created":1790100775,"description":"GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-sol-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra","name":"OpenAI: GPT-6 Astra","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-6,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.750000000000002,"max_completion_cost":9.600000000000001,"max_cost":23.430000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0018846351974469474,"input_cache_write":0.023557939968086843,"max_prompt_cost":19788.66957319295,"max_completion_cost":12061.665263660465,"max_cost":29438.001784121323},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra:batch","name":"OpenAI: GPT-6 Astra (batch)","created":1788552838,"description":"GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.875000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.715000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9894.334786596475,"max_completion_cost":6030.8326318302325,"max_cost":14719.000892060661},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-astra-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra-pro","name":"OpenAI: GPT-6 Astra Pro","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-6,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.750000000000002,"max_completion_cost":9.600000000000001,"max_cost":23.430000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0018846351974469474,"input_cache_write":0.023557939968086843,"max_prompt_cost":19788.66957319295,"max_completion_cost":12061.665263660465,"max_cost":29438.001784121323},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-6-astra-pro:batch","name":"OpenAI: GPT-6 Astra Pro (batch)","created":1788552835,"description":"GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.875000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.715000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9894.334786596475,"max_completion_cost":6030.8326318302325,"max_cost":14719.000892060661},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-6-astra-pro-20260903","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":3.75e-7,"max_prompt_cost":0.315,"max_completion_cost":0.2304,"max_cost":0.507},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.00047115879936173685,"max_prompt_cost":395.77339146385896,"max_completion_cost":289.4799663278511,"max_cost":637.0066967370682},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna-pro:batch","name":"OpenAI: GPT-5.6 Luna Pro (batch)","created":1783590867,"description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.1575,"max_completion_cost":0.1152,"max_cost":0.2535},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":197.88669573192948,"max_completion_cost":144.73998316392556,"max_cost":318.5033483685341},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-luna-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":3.75e-7,"max_prompt_cost":0.315,"max_completion_cost":0.2304,"max_cost":0.507},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.00047115879936173685,"max_prompt_cost":395.77339146385896,"max_completion_cost":289.4799663278511,"max_cost":637.0066967370682},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-luna:batch","name":"OpenAI: GPT-5.6 Luna (batch)","created":1783590864,"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.1575,"max_completion_cost":0.1152,"max_cost":0.2535},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":197.88669573192948,"max_completion_cost":144.73998316392556,"max_cost":318.5033483685341},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-luna-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":2.3040000000000003,"max_cost":5.07},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2894.7996632785116,"max_cost":6370.0669673706825},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra-pro:batch","name":"OpenAI: GPT-5.6 Terra Pro (batch)","created":1783590861,"description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.575,"max_completion_cost":1.1520000000000001,"max_cost":2.535},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1447.3998316392558,"max_cost":3185.0334836853413},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-terra-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":2.3040000000000003,"max_cost":5.07},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2894.7996632785116,"max_cost":6370.0669673706825},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-terra:batch","name":"OpenAI: GPT-5.6 Terra (batch)","created":1783590857,"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.575,"max_completion_cost":1.1520000000000001,"max_cost":2.535},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1447.3998316392558,"max_cost":3185.0334836853413},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-terra-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000030000000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":6e-7,"input_cache_write":7.500000000000001e-6,"max_prompt_cost":6.3,"max_completion_cost":3.8400000000000007,"max_cost":9.372},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.037692703948938956,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0007538540789787789,"input_cache_write":0.009423175987234739,"max_prompt_cost":7915.467829277179,"max_completion_cost":4824.666105464186,"max_cost":11775.200713648528},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol-pro:batch","name":"OpenAI: GPT-5.6 Sol Pro (batch)","created":1783590854,"description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-sol-pro-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000030000000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":6e-7,"input_cache_write":7.500000000000001e-6,"max_prompt_cost":6.3,"max_completion_cost":3.8400000000000007,"max_cost":9.372},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.037692703948938956,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0007538540789787789,"input_cache_write":0.009423175987234739,"max_prompt_cost":7915.467829277179,"max_completion_cost":4824.666105464186,"max_cost":11775.200713648528},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.6-sol:batch","name":"OpenAI: GPT-5.6 Sol (batch)","created":1783590850,"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.6-sol-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-chat-latest","name":"OpenAI: GPT Chat Latest","created":1778000212,"description":"GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updates...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000045,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":3.0000000000000004,"max_completion_cost":5.760000000000001,"max_cost":7.800000000000001},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.056539055923408424,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":3769.270394893895,"max_completion_cost":7236.999158196279,"max_cost":9800.103026724128},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-chat-latest-20260505","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000045,"completion":0.00027,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":47.25,"max_completion_cost":34.56,"max_cost":76.05000000000001},"sats_pricing":{"prompt":0.056539055923408424,"completion":0.3392343355404505,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":59366.008719578844,"max_completion_cost":43421.99494917767,"max_cost":95551.00451056025},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5-pro:batch","name":"OpenAI: GPT-5.5 Pro (batch)","created":1777051896,"description":"GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000225,"completion":0.000135,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":23.625,"max_completion_cost":17.28,"max_cost":38.025000000000006},"sats_pricing":{"prompt":0.028269527961704212,"completion":0.16961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":29683.004359789422,"max_completion_cost":21710.997474588836,"max_cost":47775.502255280124},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.5-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5","name":"OpenAI: GPT-5.5","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000045,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":7.875000000000001,"max_completion_cost":5.760000000000001,"max_cost":12.675},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.056539055923408424,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":9894.334786596475,"max_completion_cost":7236.999158196279,"max_cost":15925.167418426707},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","created":1777051893,"description":"GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on hard tasks. It features a 1M+ token...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":3.9375000000000004,"max_completion_cost":2.8800000000000003,"max_cost":6.3375},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":4947.167393298238,"max_completion_cost":3618.4995790981393,"max_cost":7962.583709213353},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.5-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","created":1776797528,"description":"[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...","context_length":272000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000012,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.000045,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-6,"input_cache_write":0.0,"max_prompt_cost":3.2640000000000002,"max_completion_cost":2.8800000000000003,"max_cost":4.6080000000000005},"sats_pricing":{"prompt":0.01507708157957558,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.056539055923408424,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.003769270394893895,"input_cache_write":0.0,"max_prompt_cost":4100.966189644558,"max_completion_cost":3618.4995790981393,"max_cost":5789.599326557023},"per_request_limits":null,"top_provider":{"context_length":272000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-image-2-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.8750000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.12,"max_completion_cost":0.24000000000000005,"max_cost":0.32160000000000005},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0023557939968086848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.0,"max_prompt_cost":150.7708157957558,"max_completion_cost":301.54163159151165,"max_cost":404.0657863326256},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","created":1773748187,"description":"GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":9.375000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.06,"max_completion_cost":0.12000000000000002,"max_cost":0.16080000000000003},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0011778969984043424,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":75.3854078978779,"max_completion_cost":150.77081579575582,"max_cost":202.0328931663128},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-nano-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":6.75e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.45,"max_completion_cost":0.864,"max_cost":1.17},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.008480858388511264,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":565.3905592340842,"max_completion_cost":1085.5498737294417,"max_cost":1470.015454008619},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","created":1773748178,"description":"GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":5.625e-7,"completion":3.375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":5.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.225,"max_completion_cost":0.432,"max_cost":0.585},"sats_pricing":{"prompt":0.0007067381990426053,"completion":0.004240429194255632,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00007067381990426053,"input_cache_write":0.0,"max_prompt_cost":282.6952796170421,"max_completion_cost":542.7749368647209,"max_cost":735.0077270043095},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-mini-20260317","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000045,"completion":0.00027,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":47.25,"max_completion_cost":34.56,"max_cost":76.05000000000001},"sats_pricing":{"prompt":0.056539055923408424,"completion":0.3392343355404505,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":59366.008719578844,"max_completion_cost":43421.99494917767,"max_cost":95551.00451056025},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4-pro:batch","name":"OpenAI: GPT-5.4 Pro (batch)","created":1772734366,"description":"GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000225,"completion":0.000135,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":23.625,"max_completion_cost":17.28,"max_cost":38.025000000000006},"sats_pricing":{"prompt":0.028269527961704212,"completion":0.16961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":29683.004359789422,"max_completion_cost":21710.997474588836,"max_cost":47775.502255280124},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-pro-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4","name":"OpenAI: GPT-5.4","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":3.9375000000000004,"max_completion_cost":2.8800000000000003,"max_cost":6.3375},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":4947.167393298238,"max_completion_cost":3618.4995790981393,"max_cost":7962.583709213353},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","created":1772734352,"description":"GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-7,"input_cache_write":0.0,"max_prompt_cost":1.9687500000000002,"max_completion_cost":1.4400000000000002,"max_cost":3.16875},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0,"max_prompt_cost":2473.583696649119,"max_completion_cost":1809.2497895490696,"max_cost":3981.2918546066767},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.4-20260305","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","created":1771959164,"description":"GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.625e-6,"completion":0.000021,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.625e-7,"input_cache_write":0.0,"max_prompt_cost":1.05,"max_completion_cost":2.6879999999999997,"max_cost":3.4019999999999997},"sats_pricing":{"prompt":0.0032981115955321577,"completion":0.02638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00032981115955321575,"input_cache_write":0.0,"max_prompt_cost":1319.2446382128633,"max_completion_cost":3377.2662738249296,"max_cost":4274.352627809676},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.3-codex-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-audio","name":"OpenAI: GPT Audio","created":1768862569,"description":"The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4800000000000001,"max_completion_cost":0.24576000000000003,"max_cost":0.66432},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":603.0832631830233,"max_completion_cost":308.77863074970793,"max_cost":834.6672362453041},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-audio","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-audio-mini","name":"OpenAI: GPT Audio Mini","created":1768859419,"description":"A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.60 per million...","context_length":128000,"architecture":{"modality":"text+audio->text+audio","input_modalities":["text","audio"],"output_modalities":["text","audio"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1152,"max_completion_cost":0.0589824,"max_cost":0.1594368},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.004523124473872674,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":144.73998316392556,"max_completion_cost":74.10687137992988,"max_cost":200.32013669887297},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-audio-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","created":1768409315,"description":"GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.625e-6,"completion":0.000021,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.625e-7,"input_cache_write":0.0,"max_prompt_cost":1.05,"max_completion_cost":2.6879999999999997,"max_cost":3.4019999999999997},"sats_pricing":{"prompt":0.0032981115955321577,"completion":0.02638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00032981115955321575,"input_cache_write":0.0,"max_prompt_cost":1319.2446382128633,"max_completion_cost":3377.2662738249296,"max_cost":4274.352627809676},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-codex-20260114","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","created":1765389783,"description":"GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.625e-6,"completion":0.000021,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.625e-7,"input_cache_write":0.0,"max_prompt_cost":0.33599999999999997,"max_completion_cost":0.6719999999999999,"max_cost":0.9239999999999999},"sats_pricing":{"prompt":0.0032981115955321577,"completion":0.02638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00032981115955321575,"input_cache_write":0.0,"max_prompt_cost":422.1582842281162,"max_completion_cost":844.3165684562324,"max_cost":1160.9352816273195},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-chat-20251211","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000315,"completion":0.000252,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.6,"max_completion_cost":32.256,"max_cost":40.824},"sats_pricing":{"prompt":0.03957733914638589,"completion":0.31661871317108714,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":15830.935658554357,"max_completion_cost":40527.19528589916,"max_cost":51292.23153371612},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2-pro:batch","name":"OpenAI: GPT-5.2 Pro (batch)","created":1765389780,"description":"GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that require step-by-step reasoning,...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.00001575,"completion":0.000126,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.3,"max_completion_cost":16.128,"max_cost":20.412},"sats_pricing":{"prompt":0.019788669573192946,"completion":0.15830935658554357,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7915.467829277179,"max_completion_cost":20263.59764294958,"max_cost":25646.11576685806},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-pro-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2","name":"OpenAI: GPT-5.2","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.625e-6,"completion":0.000021,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.625e-7,"input_cache_write":0.0,"max_prompt_cost":1.05,"max_completion_cost":2.6879999999999997,"max_cost":3.4019999999999997},"sats_pricing":{"prompt":0.0032981115955321577,"completion":0.02638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00032981115955321575,"input_cache_write":0.0,"max_prompt_cost":1319.2446382128633,"max_completion_cost":3377.2662738249296,"max_cost":4274.352627809676},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","created":1765389775,"description":"GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.3125e-6,"completion":0.0000105,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.3125e-7,"input_cache_write":0.0,"max_prompt_cost":0.525,"max_completion_cost":1.3439999999999999,"max_cost":1.7009999999999998},"sats_pricing":{"prompt":0.0016490557977660789,"completion":0.01319244638212863,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00016490557977660787,"input_cache_write":0.0,"max_prompt_cost":659.6223191064316,"max_completion_cost":1688.6331369124648,"max_cost":2137.176313904838},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.2-20251211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","created":1764878934,"description":"GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasoning stack and trained on agentic...","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-7,"input_cache_write":0.0,"max_prompt_cost":0.7500000000000001,"max_completion_cost":1.9200000000000004,"max_cost":2.4300000000000006},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0,"max_prompt_cost":942.3175987234738,"max_completion_cost":2412.333052732093,"max_cost":3053.1090198640554},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.1-codex-max-20251204","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1","name":"OpenAI: GPT-5.1","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-7,"input_cache_write":0.0,"max_prompt_cost":0.7500000000000001,"max_completion_cost":1.9200000000000004,"max_cost":2.4300000000000006},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0,"max_prompt_cost":942.3175987234738,"max_completion_cost":2412.333052732093,"max_cost":3053.1090198640554},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","created":1763060305,"description":"GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":9.375000000000001e-7,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":9.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.37500000000000006,"max_completion_cost":0.9600000000000002,"max_cost":1.2150000000000003},"sats_pricing":{"prompt":0.0011778969984043424,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00011778969984043421,"input_cache_write":0.0,"max_prompt_cost":471.1587993617369,"max_completion_cost":1206.1665263660466,"max_cost":1526.5545099320277},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.1-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","created":1763060298,"description":"GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":0.0,"max_prompt_cost":0.7500000000000001,"max_completion_cost":1.9200000000000004,"max_cost":2.4300000000000006},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00024500257566810316,"input_cache_write":0.0,"max_prompt_cost":942.3175987234738,"max_completion_cost":2412.333052732093,"max_cost":3053.1090198640554},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.1-codex-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","created":1763057820,"description":"GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex","context_length":400000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.15,"max_completion_cost":0.384,"max_cost":0.486},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":188.46351974469474,"max_completion_cost":482.46661054641856,"max_cost":610.621803972811},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5.1-codex-mini-20251113","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","created":1761752836,"description":"gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.0147456,"max_completion_cost":0.0294912,"max_cost":0.036864},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007067381990426053,"input_cache_write":0.0,"max_prompt_cost":18.52671784498247,"max_completion_cost":37.05343568996494,"max_cost":46.31679461245618},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-oss-safeguard-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","created":1760624583,"description":"GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["file","image","text"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.000012,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.5000000000000002,"max_completion_cost":0.384,"max_cost":1.4040000000000004},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.01507708157957558,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469476,"max_completion_cost":482.46661054641856,"max_cost":1764.0185448103432},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-image-mini","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-5-image","name":"OpenAI: GPT-5 Image","created":1760447986,"description":"[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...","context_length":400000,"architecture":{"modality":"text+image+file->text+image","input_modalities":["image","text","file"],"output_modalities":["image","text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.00006000000000000001,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.8750000000000003e-6,"input_cache_write":0.0,"max_prompt_cost":6.000000000000001,"max_completion_cost":1.9200000000000004,"max_cost":6.000000000000002},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.07538540789787791,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0023557939968086848,"input_cache_write":0.0,"max_prompt_cost":7538.54078978779,"max_completion_cost":2412.333052732093,"max_cost":7538.540789787792},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-image","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-5-pro","name":"OpenAI: GPT-5 Pro","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.0000225,"completion":0.00018,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.0,"max_completion_cost":23.040000000000003,"max_cost":29.160000000000004},"sats_pricing":{"prompt":0.028269527961704212,"completion":0.2261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":11307.811184681685,"max_completion_cost":28947.996632785114,"max_cost":36637.30823836866},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"image_pricing":null},{"id":"gpt-5-pro:batch","name":"OpenAI: GPT-5 Pro (batch)","created":1759776663,"description":"GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.00001125,"completion":0.00009,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.5,"max_completion_cost":11.520000000000001,"max_cost":14.580000000000002},"sats_pricing":{"prompt":0.014134763980852106,"completion":0.11307811184681685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5653.905592340842,"max_completion_cost":14473.998316392557,"max_cost":18318.65411918433},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-pro-2025-10-06","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high"],"default_effort":"high"},"image_pricing":null},{"id":"gpt-5","name":"OpenAI: GPT-5","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-7,"input_cache_write":0.0,"max_prompt_cost":0.7500000000000001,"max_completion_cost":1.9200000000000004,"max_cost":2.4300000000000006},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0,"max_prompt_cost":942.3175987234738,"max_completion_cost":2412.333052732093,"max_cost":3053.1090198640554},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5:batch","name":"OpenAI: GPT-5 (batch)","created":1754587413,"description":"GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and accuracy...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":9.375000000000001e-7,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":9.375e-8,"input_cache_write":0.0,"max_prompt_cost":0.37500000000000006,"max_completion_cost":0.9600000000000002,"max_cost":1.2150000000000003},"sats_pricing":{"prompt":0.0011778969984043424,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00011778969984043421,"input_cache_write":0.0,"max_prompt_cost":471.1587993617369,"max_completion_cost":1206.1665263660466,"max_cost":1526.5545099320277},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-mini","name":"OpenAI: GPT-5 Mini","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.15,"max_completion_cost":0.384,"max_cost":0.486},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":188.46351974469474,"max_completion_cost":482.46661054641856,"max_cost":610.621803972811},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","created":1754587407,"description":"GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.875e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.075,"max_completion_cost":0.192,"max_cost":0.243},"sats_pricing":{"prompt":0.00023557939968086843,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00002355793996808684,"input_cache_write":0.0,"max_prompt_cost":94.23175987234737,"max_completion_cost":241.23330527320928,"max_cost":305.3109019864055},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-mini-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-nano","name":"OpenAI: GPT-5 Nano","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.03,"max_completion_cost":0.0768,"max_cost":0.0972},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.0,"max_prompt_cost":37.69270394893895,"max_completion_cost":96.4933221092837,"max_cost":122.1243607945622},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","created":1754587402,"description":"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.75e-8,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.7500000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.015,"max_completion_cost":0.0384,"max_cost":0.0486},"sats_pricing":{"prompt":0.00004711587993617368,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":4.711587993617369e-6,"input_cache_write":0.0,"max_prompt_cost":18.846351974469474,"max_completion_cost":48.24666105464185,"max_cost":61.0621803972811},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-5-nano-2025-08-07","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-120b","name":"OpenAI: gpt-oss-120b","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.0294912,"max_completion_cost":0.0589824,"max_cost":0.073728},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":37.05343568996494,"max_completion_cost":74.10687137992988,"max_cost":92.63358922491236},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-120b:batch","name":"OpenAI: gpt-oss-120b (batch)","created":1754414231,"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.44e-8,"completion":2.04e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0058195968,"max_completion_cost":0.024064656,"max_cost":0.0246466512},"sats_pricing":{"prompt":0.00005578520184442965,"completion":0.0002563103868527848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.311877976153083,"max_completion_cost":30.235398474701913,"max_cost":30.966630900478698},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-oss-120b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-20b","name":"OpenAI: gpt-oss-20b","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.499999999999999e-8,"completion":1.9499999999999999e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.005898239999999999,"max_completion_cost":0.02300298,"max_cost":0.02359284},"sats_pricing":{"prompt":0.000056539055923408416,"completion":0.00024500257566810316,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":7.410687137992988,"max_completion_cost":28.90148383611212,"max_cost":29.64259778115616},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-oss-20b:batch","name":"OpenAI: gpt-oss-20b (batch)","created":1754414229,"description":"gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.6e-8,"completion":1.68e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004718592,"max_completion_cost":0.019817952,"max_cost":0.02028984},"sats_pricing":{"prompt":0.000045231244738726736,"completion":0.0002110791421140581,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.928549710394391,"max_completion_cost":24.89973992034275,"max_cost":25.492631076377982},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-oss-20b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"o3-pro","name":"OpenAI: o3 Pro","created":1749598352,"description":"The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","file","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000030000000000000004,"completion":0.00012000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.000000000000001,"max_completion_cost":12.000000000000002,"max_cost":15.000000000000002},"sats_pricing":{"prompt":0.037692703948938956,"completion":0.15077081579575582,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7538.54078978779,"max_completion_cost":15077.08157957558,"max_cost":18846.351974469475},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/o3-pro-2025-06-10","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o3","name":"OpenAI: o3","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000012,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.6,"max_completion_cost":1.2,"max_cost":1.5},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":753.854078978779,"max_completion_cost":1507.708157957558,"max_cost":1884.6351974469474},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o3:batch","name":"OpenAI: o3 (batch)","created":1744823457,"description":"o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following....","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.3,"max_completion_cost":0.6,"max_cost":0.75},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":376.9270394893895,"max_completion_cost":753.854078978779,"max_cost":942.3175987234737},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/o3-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"o4-mini:batch","name":"OpenAI: o4 Mini (batch)","created":1744820942,"description":"OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.0625e-7,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.33,"max_cost":0.41250000000000003},"sats_pricing":{"prompt":0.0010365493585958211,"completion":0.0041461974343832845,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0002591373396489553,"input_cache_write":0.0,"max_prompt_cost":207.30987171916422,"max_completion_cost":414.61974343832844,"max_cost":518.2746792979106},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/o4-mini-2025-04-16","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-4.1","name":"OpenAI: GPT-4.1","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000012,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":3.142728,"max_completion_cost":0.393216,"max_cost":3.43764},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":3948.597203201367,"max_completion_cost":494.0458091995326,"max_cost":4319.1315601010165},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1:batch","name":"OpenAI: GPT-4.1 (batch)","created":1744651385,"description":"GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":1.571364,"max_completion_cost":0.196608,"max_cost":1.71882},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":1974.2986016006835,"max_completion_cost":247.0229045997663,"max_cost":2159.5657800505082},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":6e-7,"completion":2.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.6285455999999999,"max_completion_cost":0.0786432,"max_cost":0.687528},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.0030154163159151156,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":789.7194406402733,"max_completion_cost":98.80916183990651,"max_cost":863.8263120202033},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-mini:batch","name":"OpenAI: GPT-4.1 Mini (batch)","created":1744651381,"description":"GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.31427279999999996,"max_completion_cost":0.0393216,"max_cost":0.343764},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0015077081579575578,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":394.85972032013666,"max_completion_cost":49.404580919953254,"max_cost":431.91315601010166},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-mini-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.15713639999999998,"max_completion_cost":0.5656907999999999,"max_cost":0.5814045},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":197.42986016006833,"max_completion_cost":710.7471950346144,"max_cost":730.4902564360292},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":942818,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4.1-nano:batch","name":"OpenAI: GPT-4.1 Nano (batch)","created":1744651369,"description":"For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...","context_length":1047576,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.07856819999999999,"max_completion_cost":0.0098304,"max_cost":0.085941},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00002355793996808684,"input_cache_write":0.0,"max_prompt_cost":98.71493008003416,"max_completion_cost":12.351145229988314,"max_cost":107.97828900252541},"per_request_limits":null,"top_provider":{"context_length":1047576,"max_completion_tokens":32768,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4.1-nano-2025-04-14","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"o3-mini:batch","name":"OpenAI: o3 Mini (batch)","created":1738351721,"description":"OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...","context_length":200000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":4.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.165,"max_completion_cost":0.33,"max_cost":0.41250000000000003},"sats_pricing":{"prompt":0.0010365493585958211,"completion":0.0041461974343832845,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0005182746792979106,"input_cache_write":0.0,"max_prompt_cost":207.30987171916422,"max_completion_cost":414.61974343832844,"max_cost":518.2746792979106},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":100000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/o3-mini-2025-01-31","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","created":1732127594,"description":"The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8750000000000003e-6,"input_cache_write":0.0,"max_prompt_cost":0.4800000000000001,"max_completion_cost":0.24576000000000003,"max_cost":0.66432},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0023557939968086848,"input_cache_write":0.0,"max_prompt_cost":603.0832631830233,"max_completion_cost":308.77863074970793,"max_cost":834.6672362453041},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-2024-11-20","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","created":1722902400,"description":"The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o (\"o\" for \"omni\") is...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8750000000000003e-6,"input_cache_write":0.0,"max_prompt_cost":0.4800000000000001,"max_completion_cost":0.24576000000000003,"max_cost":0.66432},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0023557939968086848,"input_cache_write":0.0,"max_prompt_cost":603.0832631830233,"max_completion_cost":308.77863074970793,"max_cost":834.6672362453041},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-2024-08-06","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini","name":"OpenAI: GPT-4o-mini","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.0288,"max_completion_cost":0.0147456,"max_cost":0.0398592},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":36.18499579098139,"max_completion_cost":18.52671784498247,"max_cost":50.08003417471824},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.0288,"max_completion_cost":0.0147456,"max_cost":0.0398592},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":36.18499579098139,"max_completion_cost":18.52671784498247,"max_cost":50.08003417471824},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-mini-2024-07-18","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-mini:batch","name":"OpenAI: GPT-4o-mini (batch)","created":1721260800,"description":"GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":5.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.0144,"max_completion_cost":0.0073728,"max_cost":0.0199296},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00007067381990426053,"input_cache_write":0.0,"max_prompt_cost":18.092497895490695,"max_completion_cost":9.263358922491236,"max_cost":25.04001708735912},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o","name":"OpenAI: GPT-4o","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8750000000000003e-6,"input_cache_write":0.0,"max_prompt_cost":0.4800000000000001,"max_completion_cost":0.24576000000000003,"max_cost":0.66432},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0023557939968086848,"input_cache_write":0.0,"max_prompt_cost":603.0832631830233,"max_completion_cost":308.77863074970793,"max_cost":834.6672362453041},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o-2024-05-13","name":"OpenAI: GPT-4o (2024-05-13)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9600000000000002,"max_completion_cost":0.09216,"max_cost":1.0214400000000001},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1206.1665263660466,"max_completion_cost":115.79198653114045,"max_cost":1283.3611840534734},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o-2024-05-13","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4o:batch","name":"OpenAI: GPT-4o (batch)","created":1715558400,"description":"GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...","context_length":128000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":9.375000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.24000000000000005,"max_completion_cost":0.12288000000000002,"max_cost":0.33216},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0011778969984043424,"input_cache_write":0.0,"max_prompt_cost":301.54163159151165,"max_completion_cost":154.38931537485396,"max_cost":417.33361812265207},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4o","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4-turbo:batch","name":"OpenAI: GPT-4 Turbo (batch)","created":1712620800,"description":"The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling.\n\nTraining data: up to December 2023.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9600000000000002,"max_completion_cost":0.09216,"max_cost":1.0214400000000001},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1206.1665263660466,"max_completion_cost":115.79198653114045,"max_cost":1283.3611840534734},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4096,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4-turbo","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","created":1706140800,"description":"GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks.\n\nTraining data up to Sep 2021.","context_length":4095,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0061425,"max_completion_cost":0.011055,"max_cost":0.01167},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.71758113354525,"max_completion_cost":13.889761405184004,"max_cost":14.66246183613725},"per_request_limits":null,"top_provider":{"context_length":4095,"max_completion_tokens":3685,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-3.5-turbo-0613","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","created":1693180800,"description":"This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up...","context_length":16385,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0737325,"max_completion_cost":0.024576,"max_cost":0.0798765},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":92.63924313050471,"max_completion_cost":30.877863074970787,"max_cost":100.3587088992474},"per_request_limits":null,"top_provider":{"context_length":16385,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-3.5-turbo-16k","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-4","name":"OpenAI: GPT-4","created":1685232000,"description":"OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...","context_length":8191,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000045,"completion":0.00009,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.368595,"max_completion_cost":0.36864,"max_cost":0.552915},"sats_pricing":{"prompt":0.056539055923408424,"completion":0.11307811184681685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":463.1114070686384,"max_completion_cost":463.1679461245618,"max_cost":694.6953801309194},"per_request_limits":null,"top_provider":{"context_length":8191,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-4","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-ada-002","name":"OpenAI: Text Embedding Ada 002","created":1761865798,"description":"text-embedding-ada-002 is OpenAI's legacy text embedding model.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0012288,"max_completion_cost":0.0,"max_cost":0.0012288},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.5438931537485392,"max_completion_cost":0.0,"max_cost":1.5438931537485392},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/text-embedding-ada-002","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-3-large","name":"OpenAI: Text Embedding 3 Large","created":1761862866,"description":"text-embedding-3-large is OpenAI's most capable embedding model for both english and non-english tasks. Embeddings are a numerical representation of text that can be used to measure the relatedness between two...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9499999999999999e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0015974399999999999,"max_completion_cost":0.0,"max_cost":0.0015974399999999999},"sats_pricing":{"prompt":0.00024500257566810316,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.007061099873101,"max_completion_cost":0.0,"max_cost":2.007061099873101},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/text-embedding-3-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"text-embedding-3-small","name":"OpenAI: Text Embedding 3 Small","created":1761857455,"description":"text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.0000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00024576000000000003,"max_completion_cost":0.0,"max_cost":0.00024576000000000003},"sats_pricing":{"prompt":0.00003769270394893895,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3087786307497079,"max_completion_cost":0.0,"max_cost":0.3087786307497079},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/text-embedding-3-small","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-image-2.5-sunburst","name":"OpenAI: GPT Image 2.5 Sunburst","created":1788916368,"description":"GPT Image 2.5 Sunburst is an image generation and editing model from OpenAI, positioned as the precision-oriented tier of the GPT Image 2.5 series. It is suited to detailed creative...","context_length":400000,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000012,"completion":0.000012,"request":0.0,"image":0.0,"image_output":5.064,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-6,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":20.256,"max_cost":20.256},"sats_pricing":{"prompt":0.01507708157957558,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":6362.528426580894,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.003769270394893895,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":25450.113706323576,"max_cost":25450.113706323576},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":360000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-image-2.5-sunburst-20260908","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":3.376,"tiers":[{"resolution":"1K","quality":"low","usd":0.006},{"resolution":"1K","quality":"medium","usd":0.053},{"resolution":"1K","quality":"high","usd":0.211},{"resolution":"1K","quality":"xhigh","usd":0.422},{"resolution":"1K","quality":"max","usd":0.844},{"resolution":"1K","quality":"auto","usd":0.844}],"default_resolution":"1K","default_quality":"auto","resolutions":["1K"],"qualities":["low","medium","high","xhigh","max","auto"],"upscale":{},"unit":"token","output_token_usd":0.00003,"input_text_token_usd":8e-6,"input_image_token_usd":8e-6,"max_input_image_tokens":8192,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2.5-flare","name":"OpenAI: GPT Image 2.5 Flare","created":1788916350,"description":"GPT Image 2.5 Flare is an image generation and editing model from OpenAI, positioned as the speed-oriented tier of the GPT Image 2.5 series. It is suited to high-volume everyday...","context_length":400000,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000012,"completion":0.000012,"request":0.0,"image":0.0,"image_output":5.064,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-6,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":20.256,"max_cost":20.256},"sats_pricing":{"prompt":0.01507708157957558,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":6362.528426580894,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.003769270394893895,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":25450.113706323576,"max_cost":25450.113706323576},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":360000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-image-2.5-flare-20260908","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":3.376,"tiers":[{"resolution":"1K","quality":"low","usd":0.006},{"resolution":"1K","quality":"medium","usd":0.053},{"resolution":"1K","quality":"high","usd":0.211},{"resolution":"1K","quality":"xhigh","usd":0.422},{"resolution":"1K","quality":"max","usd":0.844},{"resolution":"1K","quality":"auto","usd":0.844}],"default_resolution":"1K","default_quality":"auto","resolutions":["1K"],"qualities":["low","medium","high","xhigh","max","auto"],"upscale":{},"unit":"token","output_token_usd":0.00003,"input_text_token_usd":8e-6,"input_image_token_usd":8e-6,"max_input_image_tokens":8192,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-2","name":"OpenAI: GPT Image 2","created":1782264714,"description":"OpenAI's latest image generation model. Supports high-fidelity image generation and editing via the dedicated Images API.","context_length":400000,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000012,"completion":0.000012,"request":0.0,"image":0.0,"image_output":1.266,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-6,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":5.064,"max_cost":5.064},"sats_pricing":{"prompt":0.01507708157957558,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":1590.6321066452235,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.003769270394893895,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":6362.528426580894,"max_cost":6362.528426580894},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":360000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-image-2","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.844,"tiers":[{"resolution":"1K","quality":"low","usd":0.006},{"resolution":"1K","quality":"medium","usd":0.053},{"resolution":"1K","quality":"high","usd":0.211},{"resolution":"1K","quality":"auto","usd":0.211}],"default_resolution":"1K","default_quality":"auto","resolutions":["1K"],"qualities":["low","medium","high","auto"],"upscale":{},"unit":"token","output_token_usd":0.00003,"input_text_token_usd":8e-6,"input_image_token_usd":8e-6,"max_input_image_tokens":8192,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-1","name":"OpenAI: GPT Image 1","created":1782264713,"description":"OpenAI's GPT Image 1 generates and edits images via the dedicated Images API. Features accurate text rendering, transparent backgrounds, and up to 16 reference images for edits.","context_length":400000,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":1.5,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.8750000000000003e-6,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":6.0,"max_cost":6.0},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":1884.6351974469474,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0023557939968086848,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":7538.540789787789,"max_cost":7538.540789787789},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":360000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-image-1","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":1.0,"tiers":[{"resolution":"1K","quality":"low","usd":0.016},{"resolution":"1K","quality":"medium","usd":0.063},{"resolution":"1K","quality":"high","usd":0.25},{"resolution":"1K","quality":"auto","usd":0.25}],"default_resolution":"1K","default_quality":"auto","resolutions":["1K"],"qualities":["low","medium","high","auto"],"upscale":{},"unit":"token","output_token_usd":0.00004,"input_text_token_usd":0.00001,"input_image_token_usd":0.00001,"max_input_image_tokens":8192,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"gpt-image-1-mini","name":"OpenAI: GPT Image 1 Mini","created":1782264713,"description":"A cost-efficient variant of GPT Image 1 for high-quality image generation at reduced latency and cost via OpenAI's dedicated Images API.","context_length":400000,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"GPT","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.312,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.248,"max_cost":1.248},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":392.00412106896505,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1568.0164842758602,"max_cost":1568.0164842758602},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":360000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openai","canonical_slug":"openai/gpt-image-1-mini","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.208,"tiers":[{"resolution":"1K","quality":"low","usd":0.006},{"resolution":"1K","quality":"medium","usd":0.015},{"resolution":"1K","quality":"high","usd":0.052},{"resolution":"1K","quality":"auto","usd":0.052}],"default_resolution":"1K","default_quality":"auto","resolutions":["1K"],"qualities":["low","medium","high","auto"],"upscale":{},"unit":"token","output_token_usd":8e-6,"input_text_token_usd":2.5e-6,"input_image_token_usd":2.5e-6,"max_input_image_tokens":8192,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":false,"endpoints":{},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"ripple-65b-preview","name":"ricursiveAI/Ripple-65B-Preview","created":1793818990,"description":"Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.3145728,"max_completion_cost":0.1179648,"max_cost":0.39321599999999995},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":395.23664735962603,"max_completion_cost":148.21374275985977,"max_cost":494.0458091995325},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"ricursiveai/ripple-65b-preview-20261104","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"hy4","name":"Tencent: Hy4","created":1793766031,"description":"The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.255e-7,"completion":1.8757499999999998e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.15e-8,"input_cache_write":0.0,"max_prompt_cost":0.655884288,"max_completion_cost":0.12292915199999999,"max_cost":0.737820672},"sats_pricing":{"prompt":0.000785892877335377,"completion":0.0023567363144074076,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003957733914638589,"input_cache_write":0.0,"max_prompt_cost":824.0684097448203,"max_completion_cost":154.45107110100386,"max_cost":927.015205236773},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-20261104","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5.3-flashx-legal","name":"Z.ai: GLM 5.3 FlashX Legal","created":1793626154,"description":"GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. It adds legal-domain mid-training and post-training with reinforcement...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.55e-7,"completion":1.8750000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.58195968,"max_completion_cost":0.24576000000000003,"max_cost":0.7549747200000001},"sats_pricing":{"prompt":0.0006973150230553705,"completion":0.0023557939968086848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":731.1877976153082,"max_completion_cost":308.77863074970793,"max_cost":948.5679536631027},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-legal-20261102","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"particle-1","name":"Particle AI: Particle-1","created":1793207893,"description":"Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as terminal workflows, codebase changes, and data...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.5e-9,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.098304,"max_cost":0.1671168},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.653905592340842e-6,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":123.51145229988315,"max_cost":209.96946890980135},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"particle-ai/particle-1-20261027","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"kimi-k3.1-pro","name":"MoonshotAI: Kimi K3.1 Pro","created":1792778188,"description":"Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":3.145728,"max_completion_cost":14.155770000000002,"max_cost":14.470344000000003},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":3952.3664735962607,"max_completion_cost":17785.641592642387,"max_cost":18180.87974771017},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3.1-pro-20261023","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"minimax-m3.1-flash","name":"MiniMax: MiniMax M3.1 Flash","created":1792379569,"description":"MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.4718592,"max_cost":0.589824},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":592.8549710394391,"max_cost":741.0687137992988},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":524288,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3.1-flash-20261019","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"},"image_pricing":null},{"id":"deepseek-v4.1-flash-1017","name":"DeepSeek: DeepSeek V4.1 Flash 1017","created":1792225624,"description":"DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.5e-9,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.3538944,"max_cost":0.5013504},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.653905592340842e-6,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":444.6412282795793,"max_cost":629.908406729404},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20261017","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glimpse","name":"Elorian: Glimpse","created":1792206629,"description":"Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.999999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":1.1520000000000001,"max_cost":1.1575296000000002},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011307811184681683,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":1447.3998316392558,"max_cost":1454.3473508311242},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":256000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"elorian/glimpse-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"beam-1.0-501b-a23b","name":"Reflection: Beam 1.0 501B A23B","created":1792160499,"description":"Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.393216,"max_completion_cost":0.196608,"max_cost":0.540672},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":494.0458091995326,"max_completion_cost":247.0229045997663,"max_cost":679.3129876493574},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"reflection/beam-1.0-501b-a23b-20261016","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"max"},"image_pricing":null},{"id":"mercury-3","name":"Inception: Mercury 3","created":1792158337,"description":"Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":5.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.15,"max_completion_cost":0.0688128,"max_cost":0.199152},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0006596223191064315,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":188.46351974469474,"max_completion_cost":86.45801660991819,"max_cost":250.21924589463632},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-3-20261019","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"ternary-bonsai-2-9b","name":"PrismML: Ternary Bonsai 2 9B","created":1792130995,"description":"Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.2000000000000002e-7,"completion":1.9499999999999999e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.031457280000000004,"max_completion_cost":0.012779519999999999,"max_cost":0.03637248},"sats_pricing":{"prompt":0.0001507708157957558,"completion":0.00024500257566810316,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":39.52366473596261,"max_completion_cost":16.05648879898481,"max_cost":45.699237350956764},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-9b-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"moondream3-preview","name":"Moondream: Moondream 3 Preview","created":1792102385,"description":"Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0144,"max_completion_cost":0.015360000000000002,"max_cost":0.027916800000000002},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.092497895490695,"max_completion_cost":19.298664421856746,"max_cost":35.07532258672463},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3-preview-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"moondream3.1-9b-a2b","name":"Moondream: Moondream 3.1","created":1792102373,"description":"Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...","context_length":32000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0144,"max_completion_cost":0.015360000000000002,"max_cost":0.027916800000000002},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.092497895490695,"max_completion_cost":19.298664421856746,"max_cost":35.07532258672463},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moondream/moondream3.1-9b-a2b-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"muse-spark-open","name":"Meta: Muse Spark Open","created":1792087069,"description":"Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":6.375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":1.9660800000000003,"max_completion_cost":6.01620225,"max_cost":6.212811},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.008009699589149526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":2470.2290459976634,"max_completion_cost":7558.897676873013,"max_cost":7805.921523790378},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-open-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"nemotron-3.5-super-vl","name":"NVIDIA: Nemotron 3.5 Super VL","created":1792076662,"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.7077885,"max_cost":0.73138155},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":889.2820796321192,"max_cost":918.924941262203},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-super-vl-20261015","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"pareto-26.10","name":"Pareto 26.10","created":1792073620,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":4.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":1.2582912,"max_completion_cost":0.6291456,"max_cost":1.7301503999999999},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.006030832631830231,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":1580.9465894385041,"max_completion_cost":790.4732947192521,"max_cost":2173.801560477943},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.10-20261015","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pareto-latest","name":"Pareto Latest","created":1791933050,"description":"This model always redirects to the latest model in the Pareto family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":4.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":1.2582912,"max_completion_cost":0.6291456,"max_cost":1.7301503999999999},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.006030832631830231,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":1580.9465894385041,"max_completion_cost":790.4732947192521,"max_cost":2173.801560477943},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~unbiased/pareto-latest","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pareto-26.9","name":"Pareto 26.9","created":1791930537,"description":"Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.9830400000000001,"max_completion_cost":1.47456,"max_cost":1.9660800000000003},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":1235.1145229988317,"max_completion_cost":1852.6717844982472,"max_cost":2470.2290459976634},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"unbiased/pareto-26.9-20260917","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"lfm-2.5-24b-a2b","name":"LiquidAI: LFM2.5-24B-A2B","created":1791912025,"description":"LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":1.05e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0096,"max_completion_cost":0.0086016,"max_cost":0.017587199999999997},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.001319244638212863,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":12.061665263660462,"max_completion_cost":10.807252076239774,"max_cost":22.096970763025965},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-24b-a2b-20261012","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-4-argon","name":"Google: Gemini 4 Argon","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":3e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000015000000000000002,"input_cache_read":1.5e-7,"input_cache_write":2.8125e-7,"max_prompt_cost":3.145728,"max_completion_cost":14.155770000000002,"max_cost":14.470344000000003},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.003769270394893895,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.018846351974469478,"input_cache_read":0.00018846351974469473,"input_cache_write":0.00035336909952130263,"max_prompt_cost":3952.3664735962607,"max_completion_cost":17785.641592642387,"max_cost":18180.87974771017},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-4-argon-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-4-argon:batch","name":"Google: Gemini 4 Argon (batch)","created":1791907477,"description":"Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":1.5e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":7.500000000000001e-6,"input_cache_read":7.5e-8,"input_cache_write":2.8125e-7,"max_prompt_cost":1.572864,"max_completion_cost":7.077885000000001,"max_cost":7.235172000000001},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0018846351974469474,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.009423175987234739,"input_cache_read":0.00009423175987234736,"input_cache_write":0.00035336909952130263,"max_prompt_cost":1976.1832367981303,"max_completion_cost":8892.820796321193,"max_cost":9090.439873855084},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-4-argon-20261013","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"summarize","name":"ScaleDown: Summarize","created":1791893360,"description":"Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.060000000000000005,"max_completion_cost":0.0,"max_cost":0.05976000000000001},"sats_pricing":{"prompt":0.0000753854078978779,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":75.3854078978779,"max_completion_cost":0.0,"max_cost":75.08386626628639},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":4000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/summarize-20260928","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"extract","name":"ScaleDown: Extract","created":1791893351,"description":"Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.000000000000001e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.060000000000000005,"max_completion_cost":0.0,"max_cost":0.006000000000000001},"sats_pricing":{"prompt":0.0000753854078978779,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":75.3854078978779,"max_completion_cost":0.0,"max_cost":7.538540789787791},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"scaledown/extract-20260928","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"muse-wonder","name":"Meta: Muse Wonder","created":1791807945,"description":"Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000030000000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":6.291456,"max_completion_cost":28.311540000000004,"max_cost":28.940688000000005},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.037692703948938956,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":7904.732947192521,"max_completion_cost":35571.283185284774,"max_cost":36361.75949542034},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-wonder-20261012","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"step-5-preview","name":"StepFun: Step 5 Preview","created":1791462849,"description":"Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":4.05e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":0.2592,"max_cost":1.6632000000000002},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.005088515033106758,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":325.6649621188325,"max_cost":2089.6835069291756},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-5-preview-20261008","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-haiku-5.5","name":"Anthropic: Claude Haiku 5.5","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.875e-7,"max_prompt_cost":0.15,"max_completion_cost":0.096,"max_cost":0.2268},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00023557939968086843,"max_prompt_cost":188.46351974469474,"max_completion_cost":120.61665263660464,"max_cost":284.95684185397846},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-haiku-5.5:batch","name":"Anthropic: Claude Haiku 5.5 (batch)","created":1791397883,"description":"Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":9.375e-8,"max_prompt_cost":0.075,"max_completion_cost":0.048,"max_cost":0.1134},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.00011778969984043421,"max_prompt_cost":94.23175987234737,"max_completion_cost":60.30832631830232,"max_cost":142.47842092698923},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-haiku-5.5-20261007","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-nano-banana-2.1","name":"Google: Nano Banana 2.1","created":1791300825,"description":"Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.25e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.000045,"web_search":0.021,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.147456,"max_completion_cost":0.6635475000000001,"max_cost":0.6782940000000001},"sats_pricing":{"prompt":0.002826952796170421,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.056539055923408424,"web_search":26.384892764257266,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":185.2671784498247,"max_completion_cost":833.696649118619,"max_cost":852.2244977447199},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-nano-banana-2.1-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"mistral-large-4-0","name":"Mistral: Mistral Large 4","created":1791294122,"description":"Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.05e-6,"completion":3.1499999999999995e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.05e-7,"input_cache_write":0.0,"max_prompt_cost":1.1010048,"max_completion_cost":0.8257535999999999,"max_cost":1.6515071999999997},"sats_pricing":{"prompt":0.001319244638212863,"completion":0.0039577339146385886,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013192446382128632,"input_cache_write":0.0,"max_prompt_cost":1383.328265758691,"max_completion_cost":1037.4961993190182,"max_cost":2074.9923986380363},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-4-0-20261006","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.1-flash","name":"inclusionAI: Ling 3.1 Flash","created":1790950024,"description":"Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":3.375e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.11249999999999999,"max_completion_cost":0.0884736,"max_cost":0.17148239999999998},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.00042404291942556315,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":141.34763980852105,"max_completion_cost":111.16030706989483,"max_cost":215.4545111884509},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.1-flash-20261002","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"claude-sonnet-5.5","name":"Anthropic: Claude Sonnet 5.5","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.0,"max_completion_cost":1.9200000000000004,"max_cost":4.5360000000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3769.2703948938947,"max_completion_cost":2412.333052732093,"max_cost":5699.13683707957},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-5.5:batch","name":"Anthropic: Claude Sonnet 5.5 (batch)","created":1790618686,"description":"Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.5,"max_completion_cost":0.9600000000000002,"max_cost":2.2680000000000002},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1884.6351974469474,"max_completion_cost":1206.1665263660466,"max_cost":2849.568418539785},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5.5-20260928","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"perceptron-mk1.5","name":"Perceptron: Perceptron Mk1.5","created":1790352661,"description":"Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...","context_length":36864,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":2.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0082944,"max_completion_cost":0.018432,"max_cost":0.0248832},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.42127878780264,"max_completion_cost":23.15839730622809,"max_cost":31.263836363407922},"per_request_limits":null,"top_provider":{"context_length":36864,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1.5-20260925","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"ember-1","name":"Fireworks: Ember-1","created":1790208461,"description":"Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.5e-7,"input_cache_write":0.0,"max_prompt_cost":4.718592,"max_completion_cost":21.233655000000002,"max_cost":21.705516000000003},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005653905592340842,"input_cache_write":0.0,"max_prompt_cost":5928.549710394391,"max_completion_cost":26678.462388963577,"max_cost":27271.319621565253},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"fireworks/ember-1-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3-prime","name":"Z.ai: GLM 5.3 Prime","created":1790199651,"description":"GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.2e-6,"completion":0.0000132,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.4e-7,"input_cache_write":0.0,"max_prompt_cost":4.199999999999999,"max_completion_cost":1.7301504,"max_cost":5.3796479999999995},"sats_pricing":{"prompt":0.005276978552851452,"completion":0.016584789737533138,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0010553957105702905,"input_cache_write":0.0,"max_prompt_cost":5276.978552851452,"max_completion_cost":2173.8015604779434,"max_cost":6759.11598045005},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-prime-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"qwen3.8-max-prime","name":"Qwen: Qwen3.8 Max Prime","created":1790191228,"description":"Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000018,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":6.0,"max_completion_cost":2.359296,"max_cost":7.572864000000001},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.022615622369363368,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":7538.540789787789,"max_completion_cost":2964.2748551971954,"max_cost":9514.724026585922},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-prime-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"},"image_pricing":null},{"id":"aion-3.5-mini","name":"AionLabs: Aion 3.5 Mini","created":1790170962,"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.05e-6,"completion":2.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7e-7,"input_cache_write":0.0,"max_prompt_cost":0.2752512,"max_completion_cost":0.0688128,"max_cost":0.3096576},"sats_pricing":{"prompt":0.001319244638212863,"completion":0.002638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00033923433554045057,"input_cache_write":0.0,"max_prompt_cost":345.83206643967276,"max_completion_cost":86.45801660991819,"max_cost":389.06107474463187},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-mini-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"image_pricing":null},{"id":"aion-3.5","name":"AionLabs: Aion 3.5","created":1790170961,"description":"Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-6,"input_cache_write":0.0,"max_prompt_cost":1.179648,"max_completion_cost":0.294912,"max_cost":1.327104},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0014134763980852105,"input_cache_write":0.0,"max_prompt_cost":1482.1374275985977,"max_completion_cost":370.5343568996494,"max_cost":1667.4046060484225},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.5-20260923","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","high","low"],"default_effort":"high"},"image_pricing":null},{"id":"solar-mini4","name":"Upstage: Solar Mini 4","created":1790160358,"description":"Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.0393216,"max_cost":0.0688128},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":49.404580919953254,"max_cost":86.45801660991819},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-mini4-20260922","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"command-a-plus","name":"Cohere: Command A+","created":1790102896,"description":"Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured...","context_length":192000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":2.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.08639999999999999,"max_completion_cost":0.14400000000000002,"max_cost":0.2016},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":108.55498737294415,"max_completion_cost":180.92497895490698,"max_cost":253.29497053686973},"per_request_limits":null,"top_provider":{"context_length":192000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-plus-05-2026","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-5.5","name":"Anthropic: Claude Opus 5.5","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000030000000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":7.500000000000001e-6,"max_prompt_cost":6.0,"max_completion_cost":3.8400000000000007,"max_cost":9.072000000000001},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.037692703948938956,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.009423175987234739,"max_prompt_cost":7538.540789787789,"max_completion_cost":4824.666105464186,"max_cost":11398.27367415914},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-5.5:batch","name":"Anthropic: Claude Opus 5.5 (batch)","created":1790094732,"description":"Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.0,"max_completion_cost":1.9200000000000004,"max_cost":4.5360000000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3769.2703948938947,"max_completion_cost":2412.333052732093,"max_cost":5699.13683707957},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5.5-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"mimo-v2.6-pro-ultraspeed","name":"Xiaomi: MiMo-V2.6-Pro-UltraSpeed","created":1790021267,"description":"MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...","context_length":1048576,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.524999999999999e-6,"completion":0.000013049999999999999,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.3999999999999994e-8,"input_cache_write":0.0,"max_prompt_cost":6.841958399999999,"max_completion_cost":1.7104895999999998,"max_cost":7.6972032},"sats_pricing":{"prompt":0.00819816310889422,"completion":0.01639632621778844,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000678468671080901,"input_cache_write":0.0,"max_prompt_cost":8596.397080071865,"max_completion_cost":2149.0992700179663,"max_cost":9670.94671508085},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-ultraspeed-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.6-flash","name":"Xiaomi: MiMo-V2.6-Flash","created":1790021264,"description":"MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.1e-7,"completion":4.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.1999999999999996e-9,"input_cache_write":0.0,"max_prompt_cost":0.22020096,"max_completion_cost":0.05505024,"max_cost":0.24772608},"sats_pricing":{"prompt":0.00026384892764257263,"completion":0.0005276978552851453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.2769785528514525e-6,"input_cache_write":0.0,"max_prompt_cost":276.66565315173824,"max_completion_cost":69.16641328793456,"max_cost":311.2488597957055},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-flash-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.6-pro","name":"Xiaomi: MiMo-V2.6-Pro","created":1790021259,"description":"MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...","context_length":1050000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","video","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.525e-7,"completion":1.305e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.4e-9,"input_cache_write":0.0,"max_prompt_cost":0.68419584,"max_completion_cost":0.17104896,"max_cost":0.76972032},"sats_pricing":{"prompt":0.0008198163108894221,"completion":0.0016396326217788441,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.784686710809011e-6,"input_cache_write":0.0,"max_prompt_cost":859.6397080071866,"max_completion_cost":214.90992700179666,"max_cost":967.0946715080851},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.6-pro-20260921","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"grok-4.7","name":"SpaceXAI: Grok 4.7","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":4.05,"max_cost":4.2},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":5088.515033106758,"max_cost":5276.978552851453},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.7-20260916","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"grok-4.7:batch","name":"SpaceXAI: Grok 4.7 (batch)","created":1790007541,"description":"Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":2.4e-6,"completion":7.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":6e-7,"input_cache_write":0.0,"max_prompt_cost":1.2,"max_completion_cost":3.2399999999999998,"max_cost":3.36},"sats_pricing":{"prompt":0.0030154163159151156,"completion":0.009046248947745347,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0007538540789787789,"input_cache_write":0.0,"max_prompt_cost":1507.708157957558,"max_completion_cost":4070.812026485406,"max_cost":4221.582842281162},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.7-20260916","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.8-omni-flash","name":"Qwen: Qwen3.8 Omni Flash","created":1789959954,"description":"Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","image","audio","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":7.05e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.4000000000000003e-8,"input_cache_write":0.0,"max_prompt_cost":0.22499999999999998,"max_completion_cost":0.09240576,"max_cost":0.28791456},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0008857785428000654,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000030154163159151164,"input_cache_write":0.0,"max_prompt_cost":282.6952796170421,"max_completion_cost":116.10076516189017,"max_cost":361.7426090889673},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-omni-flash-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"ternary-bonsai-2-27b","name":"PrismML: Ternary Bonsai 2 27B","created":1789754046,"description":"Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.0294912,"max_completion_cost":0.024576,"max_cost":0.0503808},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007067381990426053,"input_cache_write":0.0,"max_prompt_cost":37.05343568996494,"max_completion_cost":30.877863074970787,"max_cost":63.299619303690115},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"prism-ml/ternary-bonsai-2-27b-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","none"],"default_effort":"xhigh"},"image_pricing":null},{"id":"glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","created":1789744020,"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.55e-7,"completion":1.8750000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.58195968,"max_completion_cost":0.24576000000000003,"max_cost":0.7549747200000001},"sats_pricing":{"prompt":0.0006973150230553705,"completion":0.0023557939968086848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":731.1877976153082,"max_completion_cost":308.77863074970793,"max_cost":948.5679536631027},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flashx-20260918","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"deepseek-pro-latest","name":"DeepSeek: DeepSeek Pro Latest","created":1789399174,"description":"This model always redirects to the latest model in the DeepSeek Pro family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.3905000000000002e-7,"completion":0.000012,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.3905000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.14580449280000002,"max_completion_cost":4.718592,"max_cost":4.8097198080000005},"sats_pricing":{"prompt":0.00017470568280333204,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00017470568280333204,"input_cache_write":0.0,"max_prompt_cost":183.1921860511867,"max_completion_cost":5928.549710394391,"max_cost":6043.044826676383},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-flash-latest","name":"DeepSeek: DeepSeek Flash Latest","created":1789399150,"description":"This model always redirects to the latest model in the DeepSeek Flash family.","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":9e-9,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.009437184,"max_completion_cost":0.7077885,"max_cost":0.7087322220000001},"sats_pricing":{"prompt":0.000011307811184681684,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.0,"max_prompt_cost":11.857099420788781,"max_completion_cost":889.2820796321192,"max_cost":890.4677940973227},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"schematron-v2-turbo","name":"Inference.net: Schematron V2 Turbo","created":1789176949,"description":"Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.499999999999999e-8,"completion":2.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.0057599999999999995,"max_completion_cost":0.0018432,"max_cost":0.007234559999999999},"sats_pricing":{"prompt":0.000056539055923408416,"completion":0.0002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":7.236999158196277,"max_completion_cost":2.315839730622809,"max_cost":9.089670942694525},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-turbo-20260902","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"schematron-v2-small","name":"Inference.net: Schematron V2 Small","created":1789176933,"description":"Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":3.45e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.0096,"max_completion_cost":0.00282624,"max_cost":0.01181184},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00043346609541279786,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":12.061665263660462,"max_completion_cost":3.55095425362164,"max_cost":14.840672940407835},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inference-net/schematron-v2-small-20260902","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gpt-astra-latest","name":"OpenAI: GPT Astra Latest","created":1789130932,"description":"This model always redirects to the latest model in the GPT Astra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-6,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.750000000000002,"max_completion_cost":9.600000000000001,"max_cost":23.430000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0018846351974469474,"input_cache_write":0.023557939968086843,"max_prompt_cost":19788.66957319295,"max_completion_cost":12061.665263660465,"max_cost":29438.001784121323},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-astra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-sol-latest","name":"OpenAI: GPT Sol Latest","created":1789130928,"description":"This model always redirects to the latest model in the GPT Sol family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.15,"max_completion_cost":1.9200000000000004,"max_cost":4.686},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3957.7339146385893,"max_completion_cost":2412.333052732093,"max_cost":5887.600356824264},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-sol-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-terra-latest","name":"OpenAI: GPT Terra Latest","created":1789130925,"description":"This model always redirects to the latest model in the GPT Terra family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.575,"max_completion_cost":0.9600000000000002,"max_cost":2.343},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1978.8669573192947,"max_completion_cost":1206.1665263660466,"max_cost":2943.800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-terra-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-luna-latest","name":"OpenAI: GPT Luna Latest","created":1789130922,"description":"This model always redirects to the latest model in the GPT Luna family.","context_length":1050000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.875e-7,"max_prompt_cost":0.1575,"max_completion_cost":0.096,"max_cost":0.2343},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00023557939968086843,"max_prompt_cost":197.88669573192948,"max_completion_cost":120.61665263660464,"max_cost":294.3800178412132},"per_request_limits":null,"top_provider":{"context_length":1050000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-luna-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"fugu-ultra-v2","name":"Sakana: Fugu Ultra v2","created":1789105383,"description":"Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000045,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":7.500000000000001,"max_completion_cost":5.760000000000001,"max_cost":12.3},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.056539055923408424,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":9423.175987234737,"max_completion_cost":7236.999158196279,"max_cost":15454.008619064969},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-v2-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"},"image_pricing":null},{"id":"fugu-max","name":"Sakana: Fugu Max","created":1789104771,"description":"Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":3.0,"max_completion_cost":1.1520000000000001,"max_cost":3.7680000000000002},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":3769.2703948938947,"max_completion_cost":1447.3998316392558,"max_cost":4734.203615986732},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-max-20260911","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.0-flash-vl","name":"inclusionAI: Ling 3.0 Flash VL","created":1789056114,"description":"Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.999999999999999e-8,"completion":2.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8e-8,"input_cache_write":0.0,"max_prompt_cost":0.011796479999999998,"max_completion_cost":0.00884736,"max_cost":0.017694719999999997},"sats_pricing":{"prompt":0.00011307811184681683,"completion":0.00033923433554045057,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000022615622369363368,"input_cache_write":0.0,"max_prompt_cost":14.821374275985976,"max_completion_cost":11.116030706989484,"max_cost":22.23206141397896},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-vl-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"deepseek-v4.1-flash","name":"DeepSeek: DeepSeek V4.1 Flash","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":6.75e-8,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.6999999999999997e-8,"input_cache_write":0.0,"max_prompt_cost":0.07077888,"max_completion_cost":0.7077885,"max_cost":0.714866415},"sats_pricing":{"prompt":0.00008480858388511264,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003392343355404505,"input_cache_write":0.0,"max_prompt_cost":88.92824565591587,"max_completion_cost":889.2820796321192,"max_cost":898.1749381211444},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-v4.1-flash:batch","name":"DeepSeek: DeepSeek V4.1 Flash (batch)","created":1789021285,"description":"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.68e-7,"completion":5.04e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.04e-9,"input_cache_write":0.0,"max_prompt_cost":0.176160768,"max_completion_cost":0.066060288,"max_cost":0.22020096},"sats_pricing":{"prompt":0.0002110791421140581,"completion":0.0006332374263421743,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.332374263421744e-6,"input_cache_write":0.0,"max_prompt_cost":221.3325225213906,"max_completion_cost":82.99969594552147,"max_cost":276.66565315173824},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4.1-flash-20260910","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"mercury-2.5","name":"Inception: Mercury 2.5","created":1788892137,"description":"Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...","context_length":260000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.000000000000001e-8,"completion":2.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.015600000000000003,"max_completion_cost":0.0147456,"max_cost":0.026413440000000003},"sats_pricing":{"prompt":0.0000753854078978779,"completion":0.0002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.538540789787791e-6,"input_cache_write":0.0,"max_prompt_cost":19.600206053448257,"max_completion_cost":18.52671784498247,"max_cost":33.1864658064354},"per_request_limits":null,"top_provider":{"context_length":260000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2.5-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"nex-n2.5-mini","name":"Nex AGI: Nex-N2.5-Mini","created":1788890061,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.75e-8,"completion":1.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.7500000000000005e-9,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.03538935,"max_cost":0.0363724125},"sats_pricing":{"prompt":0.00004711587993617368,"completion":0.00018846351974469473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.711587993617369e-6,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":44.464009749846085,"max_cost":45.69915254237288},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-mini-20260908","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"},"image_pricing":null},{"id":"nex-n2.5-pro","name":"Nex AGI: Nex-N2.5-Pro","created":1788890050,"description":"Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.0294912,"max_completion_cost":0.088473375,"max_cost":0.09142256250000001},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":37.05343568996494,"max_completion_cost":111.16002437461522,"max_cost":114.86545275219561},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nex-agi/nex-n2.5-pro-20260907","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","none"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.8-max-0902","name":"Qwen: Qwen3.8 Max (0902)","created":1788469704,"description":"Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":3.0,"max_completion_cost":1.179648,"max_cost":3.7864320000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":3769.2703948938947,"max_completion_cost":1482.1374275985977,"max_cost":4757.362013292961},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-max-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"xhigh"},"image_pricing":null},{"id":"muse-spark-1.3-contributor","name":"Meta: Muse Spark 1.3 Contributor","created":1788381519,"description":"Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.1572864,"max_completion_cost":0.28311539999999996,"max_cost":0.29884409999999995},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":3.7692703948938955e-6,"input_cache_write":0.0,"max_prompt_cost":197.61832367981302,"max_completion_cost":355.7128318528476,"max_cost":375.4747396062368},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-contributor-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"muse-spark-1.3","name":"Meta: Muse Spark 1.3","created":1788378359,"description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":6.375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":1.9660800000000003,"max_completion_cost":6.01620225,"max_cost":6.212811},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.008009699589149526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":2470.2290459976634,"max_completion_cost":7558.897676873013,"max_cost":7805.921523790378},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.3-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.8-flash","name":"Google: Gemini 3.8 Flash","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.2375e-6,"completion":6.1875000000000005e-6,"request":0.0,"image":1.2375e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":6.1875000000000005e-6,"input_cache_read":1.2375e-7,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":1.2976128,"max_completion_cost":0.40550400000000003,"max_cost":1.6220160000000001},"sats_pricing":{"prompt":0.0015548240378937316,"completion":0.0077741201894686585,"request":0.001,"image":0.0015548240378937316,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0077741201894686585,"input_cache_read":0.00015548240378937317,"input_cache_write":0.00007852646656028953,"max_prompt_cost":1630.3511703584575,"max_completion_cost":509.484740737018,"max_cost":2037.938962948072},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.8-flash:batch","name":"Google: Gemini 3.8 Flash (batch)","created":1788362056,"description":"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.625e-7,"completion":2.8125e-6,"request":0.0,"image":5.625e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.8125e-6,"input_cache_read":5.625e-8,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":0.589824,"max_completion_cost":0.18432,"max_cost":0.73728},"sats_pricing":{"prompt":0.0007067381990426053,"completion":0.0035336909952130265,"request":0.001,"image":0.0007067381990426053,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0035336909952130265,"input_cache_read":0.00007067381990426053,"input_cache_write":0.00007852646656028953,"max_prompt_cost":741.0687137992988,"max_completion_cost":231.5839730622809,"max_cost":926.3358922491236},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.8-flash-20260902","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-fable-5.1","name":"Anthropic: Claude Fable 5.1","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.000000000000002,"max_completion_cost":9.600000000000001,"max_cost":22.680000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.023557939968086843,"max_prompt_cost":18846.351974469475,"max_completion_cost":12061.665263660465,"max_cost":28495.684185397848},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5.1:batch","name":"Anthropic: Claude Fable 5.1 (batch)","created":1788285838,"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.875e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00023557939968086843,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-fable-5.1-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"granite-4.2-8b","name":"IBM: Granite 4.2 8B","created":1788206780,"description":"Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.999999999999999e-8,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.011796479999999998,"max_completion_cost":0.0442365,"max_cost":0.04541622},"sats_pricing":{"prompt":0.00011307811184681683,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":14.821374275985976,"max_completion_cost":55.579776607907924,"max_cost":57.062004497996},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"ibm-granite/granite-4.2-8b-20260831","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"hy4-preview","name":"Tencent: Hy4 preview","created":1787897375,"description":"Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.251e-6,"completion":3.7514999999999996e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.3e-8,"input_cache_write":0.0,"max_prompt_cost":1.311768576,"max_completion_cost":0.24009599999999998,"max_cost":1.4718005760000001},"sats_pricing":{"prompt":0.001571785754670754,"completion":0.004713472628814815,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007915467829277178,"input_cache_write":0.0,"max_prompt_cost":1648.1368194896406,"max_completion_cost":301.66224824414815,"max_cost":1849.2047794348607},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":64000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy4-preview-20260827","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-flash-latest","name":"Z.ai: GLM Flash Latest","created":1787817633,"description":"This model always redirects to the latest model in the GLM Flash family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":4.275e-8,"completion":1.3845e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.275e-8,"input_cache_write":0.0,"max_prompt_cost":0.044826624,"max_completion_cost":0.0181469184,"max_cost":0.05737021440000001},"sats_pricing":{"prompt":0.000053712103127238,"completion":0.00017395182872435324,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000053712103127238,"input_cache_write":0.0,"max_prompt_cost":56.321222248746714,"max_completion_cost":22.800214094558427,"max_cost":72.08128356221181},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"qwen3.8-flash","name":"Qwen: Qwen3.8 Flash","created":1787773060,"description":"Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":7.05e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.4000000000000003e-8,"input_cache_write":0.0,"max_prompt_cost":0.22499999999999998,"max_completion_cost":0.09240576,"max_cost":0.28791456},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0008857785428000654,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000030154163159151164,"input_cache_write":0.0,"max_prompt_cost":282.6952796170421,"max_completion_cost":116.10076516189017,"max_cost":361.7426090889673},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"glm-5.3-flash","name":"Z.ai: GLM 5.3 Flash","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.235929375,"max_completion_cost":0.70778775,"max_cost":0.7313808},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":296.4272028244399,"max_completion_cost":889.2811373145205,"max_cost":918.9239989446044},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3-flash:batch","name":"Z.ai: GLM 5.3 Flash (batch)","created":1787752741,"description":"GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":2.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.03538944,"max_cost":0.10420224},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00033923433554045057,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":44.46412282795794,"max_cost":130.92213943787613},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-flash-20260826","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","created":1787336476,"description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-9,"input_cache_write":0.0,"max_prompt_cost":0.1572864,"max_completion_cost":0.28311539999999996,"max_cost":0.29884409999999995},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":3.7692703948938955e-6,"input_cache_write":0.0,"max_prompt_cost":197.61832367981302,"max_completion_cost":355.7128318528476,"max_cost":375.4747396062368},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-contributor-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"deepseek-v4-flash-vision-exp","name":"DeepSeek: DeepSeek V4 Flash Vision Exp","created":1787311563,"description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","context_length":1048576,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":3.234e-7,"completion":9.702e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.029e-8,"input_cache_write":0.0,"max_prompt_cost":0.3391094784,"max_completion_cost":0.2543321088,"max_cost":0.5086642176},"sats_pricing":{"prompt":0.0004063273485695619,"completion":0.0012189820457086857,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000012928597454486058,"input_cache_write":0.0,"max_prompt_cost":426.0651058536769,"max_completion_cost":319.5488293902577,"max_cost":639.0976587805154},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-vision-exp-20260821","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","created":1787231581,"description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.6e-8,"completion":2.6550000000000004e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.000540672,"max_completion_cost":0.0010874880000000002,"max_cost":0.001357824},"sats_pricing":{"prompt":0.00008292394868766568,"completion":0.00033358042994810976,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6793129876493572,"max_completion_cost":1.3663454410674576,"max_cost":1.706001934892136},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-1.8b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","created":1787231561,"description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.11e-7,"completion":4.425e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.000909312,"max_completion_cost":0.00181248,"max_cost":0.002267136},"sats_pricing":{"prompt":0.0001394630046110741,"completion":0.0005559673832468495,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.142480933773919,"max_completion_cost":2.2772424017790955,"max_cost":2.848482868666055},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-30b-a3b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-latest","name":"Z.ai: GLM Latest","created":1787151053,"description":"This model always redirects to the latest GLM model from Z.ai.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.0484999999999999e-7,"completion":2.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.0335000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.10994319359999999,"max_completion_cost":1.9818078,"max_cost":1.9928021613},"sats_pricing":{"prompt":0.00013173600030154162,"completion":0.002638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001298513651040947,"input_cache_write":0.0,"max_prompt_cost":138.1352082521893,"max_completion_cost":2489.9898229699334,"max_cost":2503.8033964895526},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~z-ai/glm-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"hy-mt2-7b","name":"Tencent: Hy-MT2-7B","created":1787148797,"description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.11e-7,"completion":4.425e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.000909312,"max_completion_cost":0.00181248,"max_cost":0.002267136},"sats_pricing":{"prompt":0.0001394630046110741,"completion":0.0005559673832468495,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.142480933773919,"max_completion_cost":2.2772424017790955,"max_cost":2.848482868666055},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy-mt2-7b-20260521","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-5.3","name":"Z.ai: GLM 5.3","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.0484999999999999e-7,"completion":2.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.0335000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":0.10994319359999999,"max_completion_cost":1.9818078,"max_cost":1.9928021613},"sats_pricing":{"prompt":0.00013173600030154162,"completion":0.002638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001298513651040947,"input_cache_write":0.0,"max_prompt_cost":138.1352082521893,"max_completion_cost":2489.9898229699334,"max_cost":2503.8033964895526},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"glm-5.3:batch","name":"Z.ai: GLM 5.3 (batch)","created":1787086655,"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.75e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.7077888,"max_completion_cost":0.393216,"max_cost":1.0125312},"sats_pricing":{"prompt":0.0008480858388511263,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":889.2824565591586,"max_completion_cost":494.0458091995326,"max_cost":1272.1679586887963},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.3-20260816","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","high","low"],"default_effort":"max"},"image_pricing":null},{"id":"qwen3.8-27b","name":"Qwen: Qwen3.8 27B","created":1786722910,"description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","context_length":1024000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":2.8125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.625e-8,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.6635503125000001,"max_cost":0.6694486875000001},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0035336909952130265,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007067381990426053,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":833.7001828096141,"max_cost":841.111039564775},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-27b-20260814","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","medium","low","none"],"default_effort":"xhigh"},"image_pricing":null},{"id":"gemini-3.7-flash","name":"Google: Gemini 3.7 Flash","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":5.625e-6,"request":0.0,"image":1.125e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":5.625e-6,"input_cache_read":1.125e-7,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":1.179648,"max_completion_cost":0.36864,"max_cost":1.47456},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.007067381990426053,"request":0.001,"image":0.0014134763980852105,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.007067381990426053,"input_cache_read":0.00014134763980852105,"input_cache_write":0.00007852646656028953,"max_prompt_cost":1482.1374275985977,"max_completion_cost":463.1679461245618,"max_cost":1852.6717844982472},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.7-flash:batch","name":"Google: Gemini 3.7 Flash (batch)","created":1786640581,"description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.625e-7,"completion":2.8125e-6,"request":0.0,"image":5.625e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.8125e-6,"input_cache_read":5.625e-8,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":0.589824,"max_completion_cost":0.18432,"max_cost":0.73728},"sats_pricing":{"prompt":0.0007067381990426053,"completion":0.0035336909952130265,"request":0.001,"image":0.0007067381990426053,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0035336909952130265,"input_cache_read":0.00007067381990426053,"input_cache_write":0.00007852646656028953,"max_prompt_cost":741.0687137992988,"max_completion_cost":231.5839730622809,"max_cost":926.3358922491236},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.7-flash-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","created":1786552176,"description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.8847337500000001,"max_cost":0.9043950000000001},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":1111.6002437461523,"max_cost":1136.303099596688},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2-1-turbo-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.8-2.4t-a95b","name":"Qwen: Qwen3.8 2.4T A95B","created":1786551702,"description":"Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":3.145728,"max_completion_cost":1.179648,"max_cost":3.9321600000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":3952.3664735962607,"max_completion_cost":1482.1374275985977,"max_cost":4940.458091995327},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.8-2.4t-a95b-20260812","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","medium","low"],"default_effort":"xhigh"},"image_pricing":null},{"id":"seed-2.0-code","name":"ByteDance Seed: Seed-2.0-Code","created":1786550701,"description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.589824,"max_cost":0.6881280000000001},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":741.0687137992988,"max_cost":864.5801660991821},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-code-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"deepseek-v4-pro-0813","name":"DeepSeek: DeepSeek V4 Pro 0813","created":1786549364,"description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.545e-7,"completion":6.164999999999999e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.47e-7,"input_cache_write":0.0,"max_prompt_cost":0.162004992,"max_completion_cost":5.81802147,"max_cost":5.8342220309999995},"sats_pricing":{"prompt":0.00019411742533703556,"completion":0.007745850661506953,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018469424934980085,"input_cache_write":0.0,"max_prompt_cost":203.5468733902074,"max_completion_cost":7309.898694576019,"max_cost":7330.25345956201},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-pro-20260813","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"grok-4.6","name":"SpaceXAI: Grok 4.6","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":4.05,"max_cost":4.2},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":5088.515033106758,"max_cost":5276.978552851453},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.6-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"grok-4.6:batch","name":"SpaceXAI: Grok 4.6 (batch)","created":1786548957,"description":"Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":2.4e-6,"completion":7.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":6e-7,"input_cache_write":0.0,"max_prompt_cost":1.2,"max_completion_cost":3.2399999999999998,"max_cost":3.36},"sats_pricing":{"prompt":0.0030154163159151156,"completion":0.009046248947745347,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0007538540789787789,"input_cache_write":0.0,"max_prompt_cost":1507.708157957558,"max_completion_cost":4070.812026485406,"max_cost":4221.582842281162},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.6-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"lfm-2.5-2.6b","name":"LiquidAI: LFM2.5-2.6B","created":1786470519,"description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":5.25e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0672,"max_completion_cost":0.006144,"max_cost":0.06904319999999999},"sats_pricing":{"prompt":0.0006596223191064315,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":84.43165684562324,"max_completion_cost":7.719465768742697,"max_cost":86.74749657624604},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"liquid/lfm-2.5-2.6b-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","created":1786452751,"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.05e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.02752512,"max_completion_cost":0.0707787,"max_cost":0.07353127500000001},"sats_pricing":{"prompt":0.00013192446382128632,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":34.58320664396728,"max_completion_cost":88.92801949969217,"max_cost":92.3864193187672},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-lightning-20260807","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"sakana-namazu","name":"Sakana: Sakana Namazu","created":1786410129,"description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.425e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0105,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.3735552,"max_completion_cost":0.393216,"max_cost":0.6733823999999999},"sats_pricing":{"prompt":0.0017904034375746,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":13.192446382128633,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":469.3435187395559,"max_completion_cost":494.0458091995326,"max_cost":846.0534482541995},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/namazu-20260811","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"solar-pro4","name":"Upstage: Solar Pro 4","created":1786371636,"description":"Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in office productivity, document-intensive...","context_length":524288,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.1179648,"max_completion_cost":0.1179648,"max_cost":0.2064384},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":148.21374275985977,"max_completion_cost":148.21374275985977,"max_cost":259.3740498297546},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"upstage/solar-pro4-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"muse-glimmer-30b","name":"Meta: Muse Glimmer 30B","created":1786302394,"description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.0294912,"max_cost":0.0811008},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":37.05343568996494,"max_cost":101.89694814740359},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-glimmer-30b-20260810","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"ling-3.0-tiny","name":"inclusionAI: Ling 3.0 Tiny","created":1786034890,"description":"Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.2499999999999996e-8,"completion":6.75e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.5e-9,"input_cache_write":0.0,"max_prompt_cost":0.005898239999999999,"max_completion_cost":0.016875,"max_cost":0.017148240000000002},"sats_pricing":{"prompt":0.000028269527961704208,"completion":0.00008480858388511264,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.653905592340842e-6,"input_cache_write":0.0,"max_prompt_cost":7.410687137992988,"max_completion_cost":21.20214597127816,"max_cost":21.545451118845097},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":250000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-tiny-20260806","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"muse-spark-1.2","name":"Meta: Muse Spark 1.2","created":1785959287,"description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":6.375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":1.9660800000000003,"max_completion_cost":6.01620225,"max_cost":6.212811},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.008009699589149526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":2470.2290459976634,"max_completion_cost":7558.897676873013,"max_cost":7805.921523790378},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.2-20260805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"deepseek-v4-flash-latest","name":"DeepSeek: DeepSeek V4 Flash Latest","created":1785606009,"description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":8.85e-8,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.092798976,"max_completion_cost":0.42467309999999997,"max_cost":0.433953033},"sats_pricing":{"prompt":0.00011119347664936991,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006596223191064316,"input_cache_write":0.0,"max_prompt_cost":116.5948109710897,"max_completion_cost":533.5692477792714,"max_cost":545.2287733537711},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~deepseek/deepseek-v4-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-v4-flash-0731","name":"DeepSeek: DeepSeek V4 Flash 0731","created":1785478908,"description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":8.85e-8,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.092798976,"max_completion_cost":0.42467309999999997,"max_cost":0.433953033},"sats_pricing":{"prompt":0.00011119347664936991,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006596223191064316,"input_cache_write":0.0,"max_prompt_cost":116.5948109710897,"max_completion_cost":533.5692477792714,"max_cost":545.2287733537711},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-20260731","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"inkling-small","name":"Thinking Machines: Inkling Small","created":1785443117,"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.75e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.3538944,"max_completion_cost":0.4718592,"max_cost":0.6488064},"sats_pricing":{"prompt":0.0008480858388511263,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":444.6412282795793,"max_completion_cost":592.8549710394391,"max_cost":815.1755851792287},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-small-20260730","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","created":1785190561,"description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":4.499999999999999e-8,"completion":1.9499999999999999e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9e-9,"input_cache_write":5.700000000000001e-8,"max_prompt_cost":0.04499999999999999,"max_completion_cost":0.012779519999999999,"max_cost":0.05483039999999999},"sats_pricing":{"prompt":0.000056539055923408416,"completion":0.00024500257566810316,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000011307811184681684,"input_cache_write":0.00007161613750298402,"max_prompt_cost":56.53905592340841,"max_completion_cost":16.05648879898481,"max_cost":68.89020115339672},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-flash-20260727","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"claude-opus-5","name":"Anthropic: Claude Opus 5","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-5:batch","name":"Anthropic: Claude Opus 5 (batch)","created":1784912544,"description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":4.6875000000000004e-6,"max_prompt_cost":3.7500000000000004,"max_completion_cost":2.4000000000000004,"max_cost":5.670000000000001},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.005889484992021711,"max_prompt_cost":4711.587993617369,"max_completion_cost":3015.4163159151162,"max_cost":7123.921046349462},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-opus-5-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"ling-3.0-flash","name":"inclusionAI: Ling 3.0 Flash","created":1784818580,"description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.15e-8,"completion":9.449999999999999e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.3e-9,"input_cache_write":0.0,"max_prompt_cost":0.008257536,"max_completion_cost":0.0030965759999999998,"max_cost":0.01032192},"sats_pricing":{"prompt":0.00003957733914638589,"completion":0.00011873201743915768,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.915467829277179e-6,"input_cache_write":0.0,"max_prompt_cost":10.374961993190183,"max_completion_cost":3.8906107474463187,"max_cost":12.968702491487731},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inclusionai/ling-3.0-flash-20260723","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":5.625e-6,"request":0.0,"image":1.125e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":5.625e-6,"input_cache_read":1.125e-7,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":1.179648,"max_completion_cost":0.36864,"max_cost":1.47456},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.007067381990426053,"request":0.001,"image":0.0014134763980852105,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.007067381990426053,"input_cache_read":0.00014134763980852105,"input_cache_write":0.00007852646656028953,"max_prompt_cost":1482.1374275985977,"max_completion_cost":463.1679461245618,"max_cost":1852.6717844982472},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","created":1784646733,"description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":5.625e-7,"completion":2.8125e-6,"request":0.0,"image":5.625e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.8125e-6,"input_cache_read":5.625e-8,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":0.589824,"max_completion_cost":0.18432,"max_cost":0.73728},"sats_pricing":{"prompt":0.0007067381990426053,"completion":0.0035336909952130265,"request":0.001,"image":0.0007067381990426053,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0035336909952130265,"input_cache_read":0.00007067381990426053,"input_cache_write":0.00007852646656028953,"max_prompt_cost":741.0687137992988,"max_completion_cost":231.5839730622809,"max_cost":926.3358922491236},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.6-flash-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":4.5e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":3.7500000000000005e-6,"input_cache_read":4.499999999999999e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.4718592,"max_completion_cost":0.24576000000000003,"max_cost":0.6881280000000001},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0005653905592340842,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0047115879936173695,"input_cache_read":0.000056539055923408416,"input_cache_write":0.00015705293312057888,"max_prompt_cost":592.8549710394391,"max_completion_cost":308.77863074970793,"max_cost":864.5801660991821},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","created":1784646726,"description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":1.8750000000000003e-6,"request":0.0,"image":2.25e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":1.8750000000000003e-6,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.12288000000000002,"max_cost":0.34406400000000004},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0023557939968086848,"request":0.001,"image":0.0002826952796170421,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0023557939968086848,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":154.38931537485396,"max_cost":432.29008304959103},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-lite-20260721","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"minimal"},"image_pricing":null},{"id":"longcat-2.0","name":"Meituan: LongCat 2.0","created":1784554658,"description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","context_length":1048756,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9e-9,"input_cache_write":0.0,"max_prompt_cost":0.4719402,"max_completion_cost":0.4718592,"max_cost":0.8258346},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000011307811184681684,"input_cache_write":0.0,"max_prompt_cost":592.9567413401012,"max_completion_cost":592.8549710394391,"max_cost":1037.5979696196805},"per_request_limits":null,"top_provider":{"context_length":1048756,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meituan/longcat-2.0-20260720","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supports_max_tokens":true},"image_pricing":null},{"id":"inkling","name":"Thinking Machines: Inkling","created":1784325956,"description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","context_length":524288,"architecture":{"modality":"text+image+audio->text","input_modalities":["text","image","audio"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":6.075e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.55e-7,"input_cache_write":0.0,"max_prompt_cost":0.786432,"max_completion_cost":2.866543425,"max_cost":2.9451869250000002},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.007632772549660137,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00032038798356598104,"input_cache_write":0.0,"max_prompt_cost":988.0916183990652,"max_completion_cost":3601.592422510083,"max_cost":3700.401961277029},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":471859,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thinkingmachines/inkling-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","medium","low","minimal","none"],"default_effort":"high"},"image_pricing":null},{"id":"kimi-k3","name":"MoonshotAI: Kimi K3","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.88e-7,"completion":0.000024,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7299999999999997e-7,"input_cache_write":0.0,"max_prompt_cost":0.301989888,"max_completion_cost":22.649232,"max_cost":22.679431104000003},"sats_pricing":{"prompt":0.0003618499579098139,"completion":0.03015416315915116,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0003430036059353444,"input_cache_write":0.0,"max_prompt_cost":379.427181465241,"max_completion_cost":28457.026548227816,"max_cost":28494.969411114325},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"kimi-k3:batch","name":"MoonshotAI: Kimi K3 (batch)","created":1784215858,"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.4200000000000003e-6,"completion":0.0000171,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.42e-7,"input_cache_write":0.0,"max_prompt_cost":3.5861299200000003,"max_completion_cost":0.2801664,"max_cost":3.8102630400000006},"sats_pricing":{"prompt":0.004296968250179041,"completion":0.021484841250895198,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000429696825017904,"input_cache_write":0.0,"max_prompt_cost":4505.697779899738,"max_completion_cost":352.0076390546669,"max_cost":4787.303891143471},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k3-20260715","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"muse-spark-1.1","name":"Meta: Muse Spark 1.1","created":1784215741,"description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....","context_length":1048576,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":6.375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.00375,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":1.9660800000000003,"max_completion_cost":6.01620225,"max_cost":6.212811},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.008009699589149526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":4.711587993617369,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":2470.2290459976634,"max_completion_cost":7558.897676873013,"max_cost":7805.921523790378},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta/muse-spark-1.1-20260709","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-4.5","name":"SpaceXAI: Grok 4.5","created":1783523154,"description":"Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":4.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":4.05,"max_cost":4.2},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0005653905592340842,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":5088.515033106758,"max_cost":5276.978552851453},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.5-20260708","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"grok-latest","name":"xAI: Grok Latest","created":1783519360,"description":"This model always redirects to the latest Grok model from xAI.","context_length":500000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":4.05,"max_cost":4.2},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":5088.515033106758,"max_cost":5276.978552851453},"per_request_limits":null,"top_provider":{"context_length":500000,"max_completion_tokens":450000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~x-ai/grok-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","created":1783443096,"description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.05e-6,"completion":2.1e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7e-7,"input_cache_write":0.0,"max_prompt_cost":0.1376256,"max_completion_cost":0.0688128,"max_cost":0.17203199999999996},"sats_pricing":{"prompt":0.001319244638212863,"completion":0.002638489276425726,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00033923433554045057,"input_cache_write":0.0,"max_prompt_cost":172.91603321983638,"max_completion_cost":86.45801660991819,"max_cost":216.14504152479546},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-mini-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"aion-3.0","name":"AionLabs: Aion-3.0","created":1783443095,"description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.125e-6,"input_cache_write":0.0,"max_prompt_cost":0.589824,"max_completion_cost":0.294912,"max_cost":0.7372799999999999},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0014134763980852105,"input_cache_write":0.0,"max_prompt_cost":741.0687137992988,"max_completion_cost":370.5343568996494,"max_cost":926.3358922491235},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-3.0-20260707","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"hy3","name":"Tencent: Hy3","created":1783344048,"description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.98e-7,"completion":7.92e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.95e-8,"input_cache_write":0.0,"max_prompt_cost":0.051904512,"max_completion_cost":0.101376,"max_cost":0.127936512},"sats_pricing":{"prompt":0.00024877184606299707,"completion":0.0009950873842519883,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00006219296151574927,"input_cache_write":0.0,"max_prompt_cost":65.2140468143383,"max_completion_cost":127.37118518425449,"max_cost":160.74243570252918},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-20260706","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.0,"max_completion_cost":1.9200000000000004,"max_cost":4.5360000000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3769.2703948938947,"max_completion_cost":2412.333052732093,"max_cost":5699.13683707957},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","created":1782843083,"description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":1.5,"max_completion_cost":0.9600000000000002,"max_cost":2.2680000000000002},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0023557939968086848,"max_prompt_cost":1884.6351974469474,"max_completion_cost":1206.1665263660466,"max_cost":2849.568418539785},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-sonnet-5-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"gemini-3.1-flash-lite-image","name":"Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)","created":1782837225,"description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":2.25e-6,"request":0.0,"image":0.0,"image_output":0.000045,"web_search":0.021,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.024576,"max_completion_cost":0.1327095,"max_cost":0.13516725000000002},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.002826952796170421,"request":0.001,"image":0.0,"image_output":0.056539055923408424,"web_search":26.384892764257266,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":30.877863074970787,"max_completion_cost":166.73932982372378,"max_cost":169.8273045947406},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-image-20260630","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"fugu-ultra","name":"Sakana: Fugu Ultra","created":1782276303,"description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000045,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":0.0,"max_prompt_cost":7.500000000000001,"max_completion_cost":5.760000000000001,"max_cost":12.3},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.056539055923408424,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.0,"max_prompt_cost":9423.175987234737,"max_completion_cost":7236.999158196279,"max_cost":15454.008619064969},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sakana/fugu-ultra-20260615","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["max","xhigh","high"],"default_effort":"xhigh"},"image_pricing":null},{"id":"gemini-3.1-flash-image","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image)","created":1781754065,"description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.00009,"web_search":0.021,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.098304,"max_completion_cost":0.147456,"max_cost":0.221184},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.11307811184681685,"web_search":26.384892764257266,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":123.51145229988315,"max_completion_cost":185.2671784498247,"max_cost":277.9007676747371},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3-pro-image","name":"Google: Nano Banana Pro (Gemini 3 Pro Image)","created":1781754054,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":131072,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":3e-6,"image_output":0.00018,"web_search":0.021,"internal_reasoning":0.000018,"input_cache_read":3e-7,"input_cache_write":5.625e-7,"max_prompt_cost":0.196608,"max_completion_cost":0.589824,"max_cost":0.6881280000000001},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.003769270394893895,"image_output":0.2261562236936337,"web_search":26.384892764257266,"internal_reasoning":0.022615622369363368,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0007067381990426053,"max_prompt_cost":247.0229045997663,"max_completion_cost":741.0687137992988,"max_cost":864.5801660991821},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"glm-5.2","name":"Z.ai: GLM 5.2","created":1781631930,"description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-9,"completion":0.0000102,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.500000000000001e-9,"input_cache_write":0.0,"max_prompt_cost":0.009437184,"max_completion_cost":9.6259236,"max_cost":9.626867322},"sats_pricing":{"prompt":0.000011307811184681684,"completion":0.012815519342639243,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.423175987234738e-6,"input_cache_write":0.0,"max_prompt_cost":11.857099420788781,"max_completion_cost":12094.23628299682,"max_cost":12095.421997462025},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.2-20260616","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["xhigh","high","none"],"default_effort":"high"},"image_pricing":null},{"id":"kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","created":1781266361,"description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":5.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":1.23862725,"max_cost":1.26222075},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.006596223191064315,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":1556.2403412446129,"max_cost":1585.883768265256},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.7-code-20260612","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true},"image_pricing":null},{"id":"claude-fable-latest","name":"Anthropic: Claude Fable Latest","created":1781029944,"description":"This model always redirects to the latest model in the Claude Fable family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.000000000000002,"max_completion_cost":9.600000000000001,"max_cost":22.680000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.023557939968086843,"max_prompt_cost":18846.351974469475,"max_completion_cost":12061.665263660465,"max_cost":28495.684185397848},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-fable-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5","name":"Anthropic: Claude Fable 5","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.000015000000000000002,"completion":0.00007500000000000001,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-6,"input_cache_write":0.000018750000000000002,"max_prompt_cost":15.000000000000002,"max_completion_cost":9.600000000000001,"max_cost":22.680000000000003},"sats_pricing":{"prompt":0.018846351974469478,"completion":0.09423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0018846351974469474,"input_cache_write":0.023557939968086843,"max_prompt_cost":18846.351974469475,"max_completion_cost":12061.665263660465,"max_cost":28495.684185397848},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","created":1781007515,"description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-5-fable-20260609","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"nemotron-3.5-content-safety","name":"NVIDIA: Nemotron 3.5 Content Safety","created":1780581864,"description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.035389199999999996,"max_cost":0.0393216},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":44.463821286326336,"max_cost":49.404580919953254},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3.5-content-safety-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","created":1780551208,"description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7999999999999997e-7,"input_cache_write":0.0,"max_prompt_cost":0.18252,"max_completion_cost":0.657072,"max_cost":0.675324},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.004523124473872674,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00022615622369363367,"input_cache_write":0.0,"max_prompt_cost":229.32241082534455,"max_completion_cost":825.5606789712405,"max_cost":848.4929200537749},"per_request_limits":null,"top_provider":{"context_length":202800,"max_completion_tokens":182520,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-ultra-550b-a55b-20260604","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":4.800000000000001e-7,"completion":1.9200000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.600000000000001e-8,"input_cache_write":6e-7,"max_prompt_cost":0.48000000000000004,"max_completion_cost":0.25165824000000003,"max_cost":0.6687436800000001},"sats_pricing":{"prompt":0.0006030832631830233,"completion":0.002412333052732093,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00012061665263660466,"input_cache_write":0.0007538540789787789,"max_prompt_cost":603.0832631830232,"max_completion_cost":316.1893178877009,"max_cost":840.2252515987989},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3.7-plus:batch","name":"Qwen: Qwen3.7 Plus (batch)","created":1780491783,"description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.45e-7,"completion":1.38e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09043968,"max_completion_cost":0.18087936,"max_cost":0.2260992},"sats_pricing":{"prompt":0.00043346609541279786,"completion":0.0017338643816511914,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":113.63053611589248,"max_completion_cost":227.26107223178496,"max_cost":284.07634028973126},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-plus-20260602","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"minimax-m3","name":"MiniMax: MiniMax M3","created":1780245374,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.999999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.9216,"max_cost":0.9271296},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011307811184681683,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":1157.9198653114045,"max_cost":1164.867384503273},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":512000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m3-20260531","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"step-3.7-flash","name":"StepFun: Step 3.7 Flash","created":1779985069,"description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.725e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0768,"max_completion_cost":0.39744,"max_cost":0.40512000000000004},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0021673304770639897,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":96.4933221092837,"max_completion_cost":499.3529419155432,"max_cost":509.0022741264716},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.7-flash-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","created":1779905091,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":4.6875000000000004e-6,"max_prompt_cost":3.7500000000000004,"max_completion_cost":2.4000000000000004,"max_cost":5.670000000000001},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.005889484992021711,"max_prompt_cost":4711.587993617369,"max_completion_cost":3015.4163159151162,"max_cost":7123.921046349462},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.8-opus-20260528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.7-max","name":"Qwen: Qwen3.7 Max","created":1779376861,"description":"Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, office and productivity tasks,...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":2.2125e-6,"completion":6.6375e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.425e-7,"input_cache_write":2.765625e-6,"max_prompt_cost":2.2125,"max_completion_cost":0.8699904,"max_cost":2.7924936000000002},"sats_pricing":{"prompt":0.0027798369162342473,"completion":0.008339510748702744,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005559673832468495,"input_cache_write":0.003474796145292809,"max_prompt_cost":2779.8369162342474,"max_completion_cost":1093.076352853966,"max_cost":3508.5544848035584},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.7-max-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"grok-build-0.1","name":"SpaceXAI: Grok Build 0.1","created":1779298123,"description":"Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...","context_length":256000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.384,"max_completion_cost":0.6912,"max_cost":0.7296},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":482.46661054641856,"max_completion_cost":868.4398989835535,"max_cost":916.6865600381952},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":230400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-build-0.1-20260520","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.25e-6,"completion":0.0000135,"request":0.0,"image":2.25e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.0000135,"input_cache_read":2.25e-7,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":2.359296,"max_completion_cost":0.884736,"max_cost":3.0965759999999998},"sats_pricing":{"prompt":0.002826952796170421,"completion":0.016961716777022528,"request":0.001,"image":0.002826952796170421,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.016961716777022528,"input_cache_read":0.0002826952796170421,"input_cache_write":0.00015705293312057888,"max_prompt_cost":2964.2748551971954,"max_completion_cost":1111.6030706989484,"max_cost":3890.610747446319},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","created":1779193800,"description":"Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":6.75e-6,"request":0.0,"image":1.125e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":6.75e-6,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":1.179648,"max_completion_cost":0.442368,"max_cost":1.5482879999999999},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.008480858388511264,"request":0.001,"image":0.0014134763980852105,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.008480858388511264,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":1482.1374275985977,"max_completion_cost":555.8015353494742,"max_cost":1945.3053737231594},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.5-flash-20260519","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low","minimal"],"default_effort":"medium"},"image_pricing":null},{"id":"perceptron-mk1","name":"Perceptron: Perceptron Mk1","created":1778597029,"description":"Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...","context_length":32768,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":2.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0073728,"max_completion_cost":0.018432,"max_cost":0.0239616},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.263358922491236,"max_completion_cost":23.15839730622809,"max_cost":30.105916498096516},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perceptron/perceptron-mk1-20260512","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":2.25e-6,"request":0.0,"image":3.75e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.25e-6,"input_cache_read":3.75e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.393216,"max_completion_cost":0.147456,"max_cost":0.516096},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.002826952796170421,"request":0.001,"image":0.00047115879936173685,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.002826952796170421,"input_cache_read":0.00004711587993617368,"input_cache_write":0.00015705293312057888,"max_prompt_cost":494.0458091995326,"max_completion_cost":185.2671784498247,"max_cost":648.4351245743865},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","created":1778168828,"description":"Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and is designed for lightweight agentic...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.875e-7,"completion":1.125e-6,"request":0.0,"image":1.875e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":1.125e-6,"input_cache_read":1.875e-8,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.073728,"max_cost":0.258048},"sats_pricing":{"prompt":0.00023557939968086843,"completion":0.0014134763980852105,"request":0.001,"image":0.00023557939968086843,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0014134763980852105,"input_cache_read":0.00002355793996808684,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":92.63358922491236,"max_cost":324.21756228719323},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-20260507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"grok-4.3","name":"SpaceXAI: Grok 4.3","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":1.8750000000000002,"max_completion_cost":3.3750000000000004,"max_cost":3.5625000000000004},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":2355.7939968086844,"max_completion_cost":4240.429194255632,"max_cost":4476.008593936501},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"},"image_pricing":null},{"id":"grok-4.3:batch","name":"SpaceXAI: Grok 4.3 (batch)","created":1777591821,"description":"Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":2.4000000000000003e-7,"input_cache_write":0.0,"max_prompt_cost":1.5,"max_completion_cost":2.7,"max_cost":2.85},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0003015416315915116,"input_cache_write":0.0,"max_prompt_cost":1884.6351974469474,"max_completion_cost":3392.3433554045055,"max_cost":3580.8068751492},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":900000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.3-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"low"},"image_pricing":null},{"id":"mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.25e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.589824,"max_completion_cost":2.35929375,"max_cost":2.477259},"sats_pricing":{"prompt":0.002826952796170421,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":741.0687137992988,"max_completion_cost":2964.2720282443993,"max_cost":3112.4863363948184},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"mistral-medium-3-5:batch","name":"Mistral: Mistral Medium 3.5 (batch)","created":1777570439,"description":"Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":5.625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.294912,"max_completion_cost":1.179646875,"max_cost":1.2386295},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.007067381990426053,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":370.5343568996494,"max_completion_cost":1482.1360141221996,"max_cost":1556.2431681974092},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.5-20260430","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-haiku-latest","name":"Anthropic: Claude Haiku Latest","created":1777318492,"description":"This model always redirects to the latest model in the Claude Haiku family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.875e-7,"max_prompt_cost":0.15,"max_completion_cost":0.096,"max_cost":0.2268},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00023557939968086843,"max_prompt_cost":188.46351974469474,"max_completion_cost":120.61665263660464,"max_cost":284.95684185397846},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-haiku-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gpt-mini-latest","name":"OpenAI: GPT Mini Latest","created":1777318471,"description":"This model always redirects to the latest model in the GPT Mini family.","context_length":400000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":6.75e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.125e-7,"input_cache_write":0.0,"max_prompt_cost":0.45,"max_completion_cost":0.864,"max_cost":1.17},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.008480858388511264,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00014134763980852105,"input_cache_write":0.0,"max_prompt_cost":565.3905592340842,"max_completion_cost":1085.5498737294417,"max_cost":1470.015454008619},"per_request_limits":null,"top_provider":{"context_length":400000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~openai/gpt-mini-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["xhigh","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-pro-latest","name":"Google: Gemini Pro Latest","created":1777318451,"description":"This model always redirects to the latest model in the Gemini Pro family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":3e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000015000000000000002,"input_cache_read":1.5e-7,"input_cache_write":2.8125e-7,"max_prompt_cost":3.145728,"max_completion_cost":14.155770000000002,"max_cost":14.470344000000003},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.003769270394893895,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.018846351974469478,"input_cache_read":0.00018846351974469473,"input_cache_write":0.00035336909952130263,"max_prompt_cost":3952.3664735962607,"max_completion_cost":17785.641592642387,"max_cost":18180.87974771017},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-pro-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"kimi-latest","name":"MoonshotAI: Kimi Latest","created":1777318428,"description":"This model always redirects to the latest model in the Kimi family.","context_length":1048576,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":2.736e-7,"completion":0.000014008199999999999,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.7e-7,"input_cache_write":0.0,"max_prompt_cost":0.2868903936,"max_completion_cost":13.2197904876,"max_cost":13.248479636399999},"sats_pricing":{"prompt":0.0003437574600143232,"completion":0.01760023118191755,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00033923433554045057,"input_cache_write":0.0,"max_prompt_cost":360.455822391979,"max_completion_cost":16609.654970536867,"max_cost":16645.70069027905},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":943718,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~moonshotai/kimi-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["max","high","low","none"],"default_effort":"max"},"image_pricing":null},{"id":"gemini-flash-latest","name":"Google: Gemini Flash Latest","created":1777318398,"description":"This model always redirects to the latest model in the Gemini Flash family.","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":1.125e-6,"completion":5.625e-6,"request":0.0,"image":1.125e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":5.625e-6,"input_cache_read":1.125e-7,"input_cache_write":6.250000000000005e-8,"max_prompt_cost":1.179648,"max_completion_cost":0.36864,"max_cost":1.47456},"sats_pricing":{"prompt":0.0014134763980852105,"completion":0.007067381990426053,"request":0.001,"image":0.0014134763980852105,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.007067381990426053,"input_cache_read":0.00014134763980852105,"input_cache_write":0.00007852646656028953,"max_prompt_cost":1482.1374275985977,"max_completion_cost":463.1679461245618,"max_cost":1852.6717844982472},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~google/gemini-flash-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-latest","name":"Anthropic: Claude Sonnet Latest","created":1777318368,"description":"This model always redirects to the latest model in the Claude Sonnet family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":3.7500000000000005e-6,"max_prompt_cost":3.0,"max_completion_cost":1.9200000000000004,"max_cost":4.5360000000000005},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0047115879936173695,"max_prompt_cost":3769.2703948938947,"max_completion_cost":2412.333052732093,"max_cost":5699.13683707957},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-sonnet-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","created":1777261368,"description":"Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window. This...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":2.7e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":5.625e-7,"max_prompt_cost":0.44999999999999996,"max_completion_cost":0.1769472,"max_cost":0.597456},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0033923433554045052,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0007067381990426053,"max_prompt_cost":565.3905592340842,"max_completion_cost":222.32061413978965,"max_cost":750.657737683909},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","created":1777261362,"description":"Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.8125e-7,"completion":1.6875e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":3.515625e-7,"max_prompt_cost":0.28125,"max_completion_cost":0.110592,"max_cost":0.37341},"sats_pricing":{"prompt":0.00035336909952130263,"completion":0.002120214597127816,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0004417113744016283,"max_prompt_cost":353.36909952130264,"max_completion_cost":138.95038383736855,"max_cost":469.1610860524431},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","created":1777260255,"description":"Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":1.35e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.31850415,"max_cost":0.3224364},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0016961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":400.17608774861475,"max_cost":405.11665891872195},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-35b-a3b-20260415","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3.6-27b","name":"Qwen: Qwen3.6 27B","created":1777255064,"description":"Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":6.75e-7,"completion":4.05e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1769472,"max_completion_cost":0.2654208,"max_cost":0.3981312},"sats_pricing":{"prompt":0.0008480858388511263,"completion":0.005088515033106758,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":222.32061413978965,"max_completion_cost":333.4809212096845,"max_cost":500.22138181452675},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-27b-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro 0423","created":1777000679,"description":"DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":2.4e-6,"completion":4.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.0250000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":2.5165824,"max_completion_cost":1.8874368,"max_cost":3.4603007999999997},"sats_pricing":{"prompt":0.0030154163159151156,"completion":0.006030832631830231,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002544257516553379,"input_cache_write":0.0,"max_prompt_cost":3161.8931788770083,"max_completion_cost":2371.4198841577563,"max_cost":4347.603120955886},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":393216,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-pro-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"},"image_pricing":null},{"id":"deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash 0423","created":1777000666,"description":"DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":1.3649999999999998e-7,"completion":2.7299999999999997e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.73e-8,"input_cache_write":0.0,"max_prompt_cost":0.1431304875,"max_completion_cost":0.25763474099999994,"max_cost":0.27194785799999993},"sats_pricing":{"prompt":0.0001715018029676722,"completion":0.0003430036059353444,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003430036059353444,"input_cache_write":0.0,"max_prompt_cost":179.83250304682687,"max_completion_cost":323.6983339824854,"max_cost":341.6816700380695},"per_request_limits":null,"top_provider":{"context_length":1048575,"max_completion_tokens":943717,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v4-flash-20260423","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["xhigh","high","none"],"default_effort":"high"},"image_pricing":null},{"id":"hy3-preview","name":"Tencent: Hy3 preview","created":1776878150,"description":"Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.999999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.07077888,"max_completion_cost":0.2123361,"max_cost":0.21941415},"sats_pricing":{"prompt":0.00033923433554045057,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011307811184681683,"input_cache_write":0.0,"max_prompt_cost":88.92824565591587,"max_completion_cost":266.78405849907654,"max_cost":275.67708660526944},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hy3-preview-20260421","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","created":1776874273,"description":"MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....","context_length":1050000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.199999999999999e-7,"completion":2.7e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.44e-7,"input_cache_write":0.0,"max_prompt_cost":0.18874367999999997,"max_completion_cost":0.6370083,"max_cost":0.6558830999999999},"sats_pricing":{"prompt":0.0009046248947745347,"completion":0.0033923433554045052,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018092497895490694,"input_cache_write":0.0,"max_prompt_cost":237.14198841577561,"max_completion_cost":800.3521754972295,"max_cost":824.0669171137439},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-pro-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mimo-v2.5","name":"Xiaomi: MiMo-V2.5","created":1776874269,"description":"MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...","context_length":1000000,"architecture":{"modality":"text+image+audio+video->text","input_modalities":["text","audio","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.2000000000000002e-7,"input_cache_write":0.0,"max_prompt_cost":0.6,"max_completion_cost":0.196608,"max_cost":0.7572864},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0001507708157957558,"input_cache_write":0.0,"max_prompt_cost":753.854078978779,"max_completion_cost":247.0229045997663,"max_cost":951.472402658592},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"xiaomi/mimo-v2.5-20260422","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-latest","name":"Anthropic: Claude Opus Latest","created":1776795361,"description":"This model always redirects to the latest model in the Claude Opus family.","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Router","instruct_type":null},"pricing":{"prompt":6e-6,"completion":0.000030000000000000004,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":7.500000000000001e-6,"max_prompt_cost":6.0,"max_completion_cost":3.8400000000000007,"max_cost":9.072000000000001},"sats_pricing":{"prompt":0.00753854078978779,"completion":0.037692703948938956,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.009423175987234739,"max_prompt_cost":7538.540789787789,"max_completion_cost":4824.666105464186,"max_cost":11398.27367415914},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"~anthropic/claude-opus-latest","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["max","xhigh","high","medium","low"],"default_effort":"high"},"image_pricing":null},{"id":"kimi-k2.6","name":"MoonshotAI: Kimi K2.6","created":1776699402,"description":"Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.75e-7,"completion":5.115e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.2555904,"max_completion_cost":1.206776835,"max_cost":1.2323364600000002},"sats_pricing":{"prompt":0.0012250128783405157,"completion":0.006426606023294091,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":321.12977597969615,"max_completion_cost":1516.2227324697517,"max_cost":1548.3364450754484},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.6-20260420","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","created":1776351100,"description":"Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":4.6875000000000004e-6,"max_prompt_cost":3.7500000000000004,"max_completion_cost":2.4000000000000004,"max_cost":5.670000000000001},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.005889484992021711,"max_prompt_cost":4711.587993617369,"max_completion_cost":3015.4163159151162,"max_cost":7123.921046349462},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.7-opus-20260416","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","xhigh","high","medium","low","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5.1","name":"Z.ai: GLM 5.1","created":1775578025,"description":"GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.1e-6,"completion":6.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.8999999999999997e-7,"input_cache_write":0.0,"max_prompt_cost":0.42577919999999997,"max_completion_cost":0.8650752,"max_cost":1.0156032000000002},"sats_pricing":{"prompt":0.002638489276425726,"completion":0.008292394868766569,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0004900051513362063,"input_cache_write":0.0,"max_prompt_cost":534.9589777738688,"max_completion_cost":1086.9007802389717,"max_cost":1276.0276915731679},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5.1-20260406","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","created":1775227989,"description":"Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":5.3999999999999994e-8,"completion":1.635e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.6999999999999997e-8,"input_cache_write":0.0,"max_prompt_cost":0.014155775999999998,"max_completion_cost":0.005357568,"max_cost":0.017743872},"sats_pricing":{"prompt":0.0000678468671080901,"completion":0.00020542523652171727,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003392343355404505,"input_cache_write":0.0,"max_prompt_cost":17.78564913118317,"max_completion_cost":6.7313741503436315,"max_cost":22.29381714012891},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-4-26b-a4b-it-20260403","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"gemma-4-31b-it","name":"Google: Gemma 4 31B","created":1775148486,"description":"Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Gemma","instruct_type":null},"pricing":{"prompt":3e-7,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.0098304,"max_cost":0.0835584},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":12.351145229988314,"max_cost":104.98473445490067},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-4-31b-it-20260402","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","created":1775133557,"description":"Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.875e-7,"completion":2.925e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":6.09375e-7,"max_prompt_cost":0.4875,"max_completion_cost":0.1916928,"max_cost":0.6472439999999999},"sats_pricing":{"prompt":0.0006125064391702579,"completion":0.0036750386350215473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0007656330489628223,"max_prompt_cost":612.5064391702579,"max_completion_cost":240.84733198477213,"max_cost":813.212549157568},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.6-plus-04-02","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","created":1775061458,"description":"GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, excels at long-horizon planning, complex coding,...","context_length":202752,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.5999999999999994e-7,"input_cache_write":0.0,"max_prompt_cost":0.3649536,"max_completion_cost":0.786432,"max_cost":0.915456},"sats_pricing":{"prompt":0.002261562236936337,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00045231244738726733,"input_cache_write":0.0,"max_prompt_cost":458.53626666331616,"max_completion_cost":988.0916183990652,"max_cost":1150.200399542662},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5v-turbo-20260401","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","created":1774979158,"description":"Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":3.7500000000000004,"max_completion_cost":6.750000000000001,"max_cost":7.125000000000001},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":4711.587993617369,"max_completion_cost":8480.858388511264,"max_cost":8952.017187873002},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-multi-agent-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"grok-4.20","name":"SpaceXAI: Grok 4.20","created":1774979019,"description":"Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...","context_length":2000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":3.7500000000000004,"max_completion_cost":6.750000000000001,"max_cost":7.125000000000001},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":4711.587993617369,"max_completion_cost":8480.858388511264,"max_cost":8952.017187873002},"per_request_limits":null,"top_provider":{"context_length":2000000,"max_completion_tokens":1800000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-4.20-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"reka-edge","name":"Reka Edge","created":1774026965,"description":"Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to deliver industry-leading performance in image understanding,...","context_length":16384,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":1.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0024576,"max_completion_cost":0.0022117499999999997,"max_cost":0.0024576},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00018846351974469473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.0877863074970784,"max_completion_cost":2.7788945986355236,"max_cost":3.0877863074970784},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-edge-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"minimax-m2.7","name":"MiniMax: MiniMax M2.7","created":1773836697,"description":"MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evolution, M2.7 integrates advanced agentic capabilities through multi-agent...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.999999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.09215999999999999,"max_completion_cost":0.2359296,"max_cost":0.2691072},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00011307811184681683,"input_cache_write":0.0,"max_prompt_cost":115.79198653114044,"max_completion_cost":296.42748551971954,"max_cost":338.1126006709301},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.7-20260318","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"mistral-small-2603","name":"Mistral: Mistral Small 4","created":1773695685,"description":"Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.18874349999999998,"max_cost":0.20054002499999998},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":237.1417622595519,"max_cost":251.96319307459382},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-2603","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["high","none"],"default_effort":"high"},"image_pricing":null},{"id":"glm-5-turbo","name":"Z.ai: GLM 5 Turbo","created":1773583573,"description":"GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-world agent workflows...","context_length":202752,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.8e-6,"completion":6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.5999999999999994e-7,"input_cache_write":0.0,"max_prompt_cost":0.3649536,"max_completion_cost":0.786432,"max_cost":0.915456},"sats_pricing":{"prompt":0.002261562236936337,"completion":0.00753854078978779,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00045231244738726733,"input_cache_write":0.0,"max_prompt_cost":458.53626666331616,"max_completion_cost":988.0916183990652,"max_cost":1150.200399542662},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-turbo-20260315","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","created":1773245239,"description":"NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...","context_length":1048576,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.6e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.4718592,"max_completion_cost":0.9437184,"max_cost":1.2976128},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.004523124473872674,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":592.8549710394391,"max_completion_cost":1185.7099420788782,"max_cost":1630.3511703584575},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":262144,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-super-120b-a12b-20230311","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["medium","low","none"],"default_effort":"medium","supports_max_tokens":true},"image_pricing":null},{"id":"seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","created":1773157231,"description":"Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practical default choice for most production workloads across...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.098304,"max_completion_cost":0.393216,"max_cost":0.442368},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":123.51145229988315,"max_completion_cost":494.0458091995326,"max_cost":555.8015353494742},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-lite-20260309","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.5-9b","name":"Qwen: Qwen3.5-9B","created":1773152396,"description":"Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architecture. It uses a unified vision-language design...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.55e-7,"completion":3.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.06684672,"max_completion_cost":0.088473375,"max_cost":0.09515820000000001},"sats_pricing":{"prompt":0.00032038798356598104,"completion":0.00047115879936173685,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":83.98778756392053,"max_completion_cost":111.16002437461522,"max_cost":119.55899536379742},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-9b-20260310","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mercury-2","name":"Inception: Mercury 2","created":1772636275,"description":"Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":1.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.048,"max_completion_cost":0.05625,"max_cost":0.0855},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.0014134763980852105,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":60.30832631830232,"max_completion_cost":70.67381990426053,"max_cost":107.424206254476},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":50000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"inception/mercury-2-20260304","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-flash-lite-preview","name":"Google: Gemini 3.1 Flash Lite Preview","created":1772512673,"description":"Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","video","file","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":2.25e-6,"request":0.0,"image":3.75e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.25e-6,"input_cache_read":3.75e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.393216,"max_completion_cost":0.147456,"max_cost":0.516096},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.002826952796170421,"request":0.001,"image":0.00047115879936173685,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.002826952796170421,"input_cache_read":0.00004711587993617368,"input_cache_write":0.00015705293312057888,"max_prompt_cost":494.0458091995326,"max_completion_cost":185.2671784498247,"max_cost":648.4351245743865},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-lite-preview-20260303","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","created":1772131107,"description":"Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four reasoning effort modes (minimal/low/medium/high), multimodal understanding,...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.0786432,"max_cost":0.098304},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":98.80916183990651,"max_cost":123.51145229988315},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-2.0-mini-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-flash-image-preview","name":"Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)","created":1772119558,"description":"Gemini 3.1 Flash Image Preview, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.00009,"web_search":0.021,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.049152,"max_completion_cost":0.265419,"max_cost":0.27033450000000003},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.11307811184681685,"web_search":26.384892764257266,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":61.75572614994157,"max_completion_cost":333.47865964744756,"max_cost":339.6546091894812},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-flash-image-preview-20260226","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true,"supported_efforts":["high","minimal","none"],"default_effort":"minimal"},"image_pricing":null},{"id":"qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","created":1772053822,"description":"The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.1e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.05505024,"max_completion_cost":0.12288,"max_cost":0.16072704},"sats_pricing":{"prompt":0.00026384892764257263,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":69.16641328793456,"max_completion_cost":154.38931537485394,"max_cost":201.94122451030893},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-35b-a3b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-27b","name":"Qwen: Qwen3.5-27B","created":1772053810,"description":"The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its overall capabilities are comparable to those of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.8999999999999997e-7,"completion":3.9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.10223615999999999,"max_completion_cost":0.319488,"max_cost":0.38977536},"sats_pricing":{"prompt":0.0004900051513362063,"completion":0.004900051513362063,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":128.45191039187847,"max_completion_cost":401.4122199746202,"max_cost":489.7229083690367},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":81920,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-27b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","created":1772053789,"description":"The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.8999999999999997e-7,"completion":3.1199999999999998e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.10223615999999999,"max_completion_cost":0.20447231999999999,"max_cost":0.28114944},"sats_pricing":{"prompt":0.0004900051513362063,"completion":0.003920041210689651,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":128.45191039187847,"max_completion_cost":256.90382078375694,"max_cost":353.2427535776658},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-122b-a10b-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","created":1772053776,"description":"The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Compared to the...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":9.749999999999999e-8,"completion":3.8999999999999997e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.09749999999999999,"max_completion_cost":0.025559039999999998,"max_cost":0.11666927999999999},"sats_pricing":{"prompt":0.00012250128783405158,"completion":0.0004900051513362063,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":122.50128783405157,"max_completion_cost":32.11297759796962,"max_cost":146.58602103252878},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-flash-20260224","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","created":1772045923,"description":"Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","audio","image","video","file"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":3e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000018,"input_cache_read":3e-7,"input_cache_write":5.625e-7,"max_prompt_cost":3.145728,"max_completion_cost":1.179648,"max_cost":4.128768},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.003769270394893895,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.022615622369363368,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0007067381990426053,"max_prompt_cost":3952.3664735962607,"max_completion_cost":1482.1374275985977,"max_cost":5187.480996595092},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-customtools-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"aion-2.0","name":"AionLabs: Aion-2.0","created":1771881306,"description":"Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging....","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":2.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.1572864,"max_completion_cost":0.0786432,"max_cost":0.196608},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.0030154163159151156,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":197.61832367981302,"max_completion_cost":98.80916183990651,"max_cost":247.0229045997663},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-2.0-20260223","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":3e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000018,"input_cache_read":3e-7,"input_cache_write":5.625e-7,"max_prompt_cost":3.145728,"max_completion_cost":1.179648,"max_cost":4.128768},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.003769270394893895,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.022615622369363368,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0007067381990426053,"max_prompt_cost":3952.3664735962607,"max_completion_cost":1482.1374275985977,"max_cost":5187.480996595092},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","created":1771509627,"description":"Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["audio","file","image","text","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":9e-6,"request":0.0,"image":1.5e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":9e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.572864,"max_completion_cost":0.589824,"max_cost":2.064384},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.011307811184681684,"request":0.001,"image":0.0018846351974469474,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.011307811184681684,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1976.1832367981303,"max_completion_cost":741.0687137992988,"max_cost":2593.740498297546},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3.1-pro-preview-20260219","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":4.5e-7,"input_cache_write":5.625e-6,"max_prompt_cost":4.5,"max_completion_cost":2.8800000000000003,"max_cost":6.804},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0005653905592340842,"input_cache_write":0.007067381990426053,"max_prompt_cost":5653.905592340842,"max_completion_cost":3618.4995790981393,"max_cost":8548.705255619354},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"claude-sonnet-4.6:batch","name":"Anthropic: Claude Sonnet 4.6 (batch)","created":1771342990,"description":"Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.25e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":2.8125e-6,"max_prompt_cost":2.25,"max_completion_cost":1.4400000000000002,"max_cost":3.402},"sats_pricing":{"prompt":0.002826952796170421,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0035336909952130265,"max_prompt_cost":2826.952796170421,"max_completion_cost":1809.2497895490696,"max_cost":4274.352627809677},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-sonnet-20260217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"medium"},"image_pricing":null},{"id":"qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","created":1771229416,"description":"The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achieving higher inference efficiency. In a variety of...","context_length":1000000,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.8999999999999997e-7,"completion":2.34e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.38999999999999996,"max_completion_cost":0.15335424,"max_cost":0.5177952},"sats_pricing":{"prompt":0.0004900051513362063,"completion":0.002940030908017238,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":490.00515133620627,"max_completion_cost":192.6778655878177,"max_cost":650.5700393260545},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-plus-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","created":1771223018,"description":"The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["text","image","video"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":5.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":1.2740166,"max_cost":1.29367785},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0067846867108090105,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0005653905592340842,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":1600.704350994459,"max_cost":1625.4072068449948},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3.5-397b-a17b-20260216","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"minimax-m2.5","name":"MiniMax: MiniMax M2.5","created":1770908502,"description":"MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.0500000000000004e-7,"completion":1.425e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":5.625e-7,"max_prompt_cost":0.08019000000000001,"max_completion_cost":0.0466944,"max_cost":0.11361336000000001},"sats_pricing":{"prompt":0.0005088515033106758,"completion":0.0017904034375746,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0007067381990426053,"max_prompt_cost":100.75259765551382,"max_completion_cost":58.66793984244449,"max_cost":142.7464914374741},"per_request_limits":null,"top_provider":{"context_length":198000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"glm-5","name":"Z.ai: GLM 5","created":1770829182,"description":"GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":4.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.304128,"max_completion_cost":0.6291456,"max_cost":0.7366656},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.006030832631830231,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":382.1135555527635,"max_completion_cost":790.4732947192521,"max_cost":925.5639456722494},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-5-20260211","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":7.500000000000001,"max_completion_cost":4.800000000000001,"max_cost":11.340000000000002},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":9423.175987234737,"max_completion_cost":6030.8326318302325,"max_cost":14247.842092698924},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","created":1770219050,"description":"Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":4.6875000000000004e-6,"max_prompt_cost":3.7500000000000004,"max_completion_cost":2.4000000000000004,"max_cost":5.670000000000001},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.005889484992021711,"max_prompt_cost":4711.587993617369,"max_completion_cost":3015.4163159151162,"max_cost":7123.921046349462},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":128000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.6-opus-20260205","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false,"supported_efforts":["max","high","medium","low","none"],"default_effort":"high","supports_max_tokens":true},"image_pricing":null},{"id":"qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","created":1770164101,"description":"Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.7999999999999997e-7,"completion":1.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.05e-7,"input_cache_write":0.0,"max_prompt_cost":0.04718591999999999,"max_completion_cost":0.2831148,"max_cost":0.2878335},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0015077081579575578,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00013192446382128632,"input_cache_write":0.0,"max_prompt_cost":59.285497103943904,"max_completion_cost":355.7120779987687,"max_cost":361.64076340289733},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-next-2025-02-03","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"step-3.5-flash","name":"StepFun: Step 3.5 Flash","created":1769728337,"description":"Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.0294912,"max_cost":0.0589824},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":37.05343568996494,"max_cost":74.10687137992988},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"stepfun/step-3.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"kimi-k2.5","name":"MoonshotAI: Kimi K2.5","created":1769487076,"description":"Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.8847337500000001,"max_cost":0.9043950000000001},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":1111.6002437461523,"max_cost":1136.303099596688},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2.5-0127","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"minimax-m2-her","name":"MiniMax: MiniMax M2-her","created":1769177239,"description":"MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in tone and personality, it supports rich message...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.0294912,"max_completion_cost":0.0036864,"max_cost":0.032256},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":37.05343568996494,"max_completion_cost":4.631679461245618,"max_cost":40.527195285899154},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2-her-20260123","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"palmyra-x5","name":"Writer: Palmyra X5","created":1769003823,"description":"Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context windows up to 1 million...","context_length":1040000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9359999999999999,"max_completion_cost":0.073728,"max_cost":1.0023552},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1176.012363206895,"max_completion_cost":92.63358922491236,"max_cost":1259.3825935093164},"per_request_limits":null,"top_provider":{"context_length":1040000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"writer/palmyra-x5-20250428","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","created":1768833913,"description":"As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning,...","context_length":200000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9.075000000000002e-8,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.011894784000000002,"max_completion_cost":0.07077839999999999,"max_cost":0.07196795099999999},"sats_pricing":{"prompt":0.00011402042944554034,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":14.944885728285863,"max_completion_cost":88.92764257265267,"max_cost":90.42222236182481},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-flash-20260119","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","created":1766505011,"description":"Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate outputs of...","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0294912,"max_completion_cost":0.0147456,"max_cost":0.0405504},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":37.05343568996494,"max_completion_cost":18.52671784498247,"max_cost":50.948474073701796},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-flash-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"seed-1.6","name":"ByteDance Seed: Seed 1.6","created":1766504997,"description":"Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.","context_length":262144,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.098304,"max_completion_cost":0.098304,"max_cost":0.18432},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":123.51145229988315,"max_completion_cost":123.51145229988315,"max_cost":231.5839730622809},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seed-1.6-20250625","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"minimax-m2.1","name":"MiniMax: MiniMax M2.1","created":1766454997,"description":"MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":5.625e-7,"max_prompt_cost":0.09215999999999999,"max_completion_cost":0.2359296,"max_cost":0.2691072},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0007067381990426053,"max_prompt_cost":115.79198653114044,"max_completion_cost":296.42748551971954,"max_cost":338.1126006709301},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"glm-4.7","name":"Z.ai: GLM 4.7","created":1766378014,"description":"GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates significant improvements in executing complex agent tasks while...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1824768,"max_completion_cost":0.4325376,"max_cost":0.49704960000000004},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.0041461974343832845,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020730987171916422,"input_cache_write":0.0,"max_prompt_cost":229.26813333165808,"max_completion_cost":543.4503901194859,"max_cost":624.5047806912842},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.7-20251222","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":4.5e-6,"request":0.0,"image":7.5e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":4.5e-6,"input_cache_read":7.5e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.786432,"max_completion_cost":0.294912,"max_cost":1.032192},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.005653905592340842,"request":0.001,"image":0.0009423175987234737,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.005653905592340842,"input_cache_read":0.00009423175987234736,"input_cache_write":0.00015705293312057888,"max_prompt_cost":988.0916183990652,"max_completion_cost":370.5343568996494,"max_cost":1296.870249148773},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-flash-preview-20251217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","created":1765987078,"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and tool...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":2.25e-6,"request":0.0,"image":3.75e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":2.25e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.393216,"max_completion_cost":0.147456,"max_cost":0.516096},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.002826952796170421,"request":0.001,"image":0.00047115879936173685,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.002826952796170421,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":494.0458091995326,"max_completion_cost":185.2671784498247,"max_cost":648.4351245743865},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-flash-preview-20251217","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"supported_efforts":["high","medium","low","minimal","none"],"default_effort":"medium"},"image_pricing":null},{"id":"nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","created":1765731275,"description":"NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.999999999999999e-8,"completion":3.5999999999999994e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.8e-8,"input_cache_write":0.0,"max_prompt_cost":0.023592959999999996,"max_completion_cost":0.08493443999999999,"max_cost":0.08729378999999998},"sats_pricing":{"prompt":0.00011307811184681683,"completion":0.00045231244738726733,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000022615622369363368,"input_cache_write":0.0,"max_prompt_cost":29.642748551971952,"max_completion_cost":106.71362339963059,"max_cost":109.67796610169489},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nvidia/nemotron-3-nano-30b-a3b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"devstral-2512","name":"Mistral: Devstral 2 2512","created":1765285419,"description":"Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...","context_length":262144,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":6e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.1572864,"max_completion_cost":0.6291450000000001,"max_cost":0.6606024},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":197.61832367981302,"max_completion_cost":790.4725408651732,"max_cost":829.9963563719516},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/devstral-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"relace-search","name":"Relace: Relace Search","created":1765213560,"description":"The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.384,"max_completion_cost":0.5760000000000001,"max_cost":0.768},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":482.46661054641856,"max_completion_cost":723.6999158196279,"max_cost":964.9332210928371},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-search-20251208","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.6v","name":"Z.ai: GLM 4.6V","created":1765207462,"description":"GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K tokens, processes complex page layouts...","context_length":131072,"architecture":{"modality":"text+image+video->text","input_modalities":["image","text","video"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.35e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":8.25e-8,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.0442368,"max_cost":0.0884736},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0016961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00010365493585958211,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":55.580153534947414,"max_cost":111.16030706989483},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6-20251208","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"nova-2-lite-v1","name":"Amazon: Nova 2 Lite","created":1764696672,"description":"Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing...","context_length":1000000,"architecture":{"modality":"text+image+file+video->text","input_modalities":["text","image","video","file"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.44999999999999996,"max_completion_cost":0.24575625000000004,"max_cost":0.6662655000000001},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":565.3905592340842,"max_completion_cost":308.7739191617143,"max_cost":837.1116080963928},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65535,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-2-lite-v1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","created":1764681735,"description":"The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.0629145,"max_cost":0.0786432},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":79.04725408651731,"max_cost":98.80916183990651},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-14b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","created":1764681654,"description":"A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":2.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.2499999999999996e-8,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.047185874999999995,"max_cost":0.05898239999999999},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000028269527961704208,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":59.28544056488798,"max_cost":74.10687137992987},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-8b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","created":1764681560,"description":"The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":1.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.0196608,"max_completion_cost":0.01572855,"max_cost":0.0196608},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00018846351974469473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":24.702290459976627,"max_completion_cost":19.761719289869458,"max_cost":24.702290459976627},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/ministral-3b-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large-2512","name":"Mistral: Mistral Large 3 2512","created":1764624472,"description":"Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apache 2.0 license.","context_length":262144,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":2.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.47185875,"max_cost":0.5111805},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":592.8544056488798,"max_cost":642.2591750323529},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":209715,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2512","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","created":1764594642,"description":"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":3.8999999999999997e-7,"completion":5.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":0.0,"max_prompt_cost":0.0638976,"max_completion_cost":0.08404992,"max_cost":0.09043968},"sats_pricing":{"prompt":0.0004900051513362063,"completion":0.0007161613750298401,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00024500257566810316,"input_cache_write":0.0,"max_prompt_cost":80.28244399492404,"max_completion_cost":105.60229171640009,"max_cost":113.63053611589248},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.2-20251201","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":false},"image_pricing":null},{"id":"claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.500000000000001e-6,"completion":0.000037500000000000003,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-7,"input_cache_write":9.375000000000001e-6,"max_prompt_cost":1.5000000000000002,"max_completion_cost":2.4000000000000004,"max_cost":3.420000000000001},"sats_pricing":{"prompt":0.009423175987234739,"completion":0.04711587993617369,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0009423175987234737,"input_cache_write":0.011778969984043422,"max_prompt_cost":1884.6351974469476,"max_completion_cost":3015.4163159151162,"max_cost":4296.968250179041},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","created":1764010580,"description":"Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["file","image","text"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":4.6875000000000004e-6,"max_prompt_cost":0.7500000000000001,"max_completion_cost":1.2000000000000002,"max_cost":1.7100000000000004},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.005889484992021711,"max_prompt_cost":942.3175987234738,"max_completion_cost":1507.7081579575581,"max_cost":2148.4841250895206},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-opus-20251124","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-3-pro-image-preview","name":"Google: Nano Banana Pro (Gemini 3 Pro Image Preview)","created":1763653797,"description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","context_length":65536,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-6,"completion":0.000018,"request":0.0,"image":3e-6,"image_output":0.00018,"web_search":0.021,"internal_reasoning":0.000018,"input_cache_read":3e-7,"input_cache_write":5.625e-7,"max_prompt_cost":0.196608,"max_completion_cost":0.589824,"max_cost":0.6881280000000001},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.022615622369363368,"request":0.001,"image":0.003769270394893895,"image_output":0.2261562236936337,"web_search":26.384892764257266,"internal_reasoning":0.022615622369363368,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0007067381990426053,"max_prompt_cost":247.0229045997663,"max_completion_cost":741.0687137992988,"max_cost":864.5801660991821},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-3-pro-image-preview-20251120","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","created":1762440622,"description":"Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.3686400000000001,"max_cost":0.5160960000000001},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":463.1679461245619,"max_cost":648.4351245743867},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-thinking-20251106","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"default_enabled":true},"image_pricing":null},{"id":"nova-premier-v1","name":"Amazon: Nova Premier 1.0","created":1761950332,"description":"Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.","context_length":1000000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000018750000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":9.375000000000001e-7,"input_cache_write":0.0,"max_prompt_cost":3.7500000000000004,"max_completion_cost":0.6000000000000001,"max_cost":4.23},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.023557939968086843,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0011778969984043424,"input_cache_write":0.0,"max_prompt_cost":4711.587993617369,"max_completion_cost":753.8540789787791,"max_cost":5314.671256800392},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-premier-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-pro-search","name":"Perplexity: Sonar Pro Search","created":1761854366,"description":"Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis. Pricing is based...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.026999999999999996,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9,"max_completion_cost":0.18000000000000002,"max_cost":1.044},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":33.92343355404505,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1130.7811184681684,"max_completion_cost":226.1562236936337,"max_cost":1311.7060974230756},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro-search","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","created":1761835144,"description":"Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding. Input audio...","context_length":32768,"architecture":{"modality":"text+file+audio->text","input_modalities":["text","audio","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5000000000000002e-8,"input_cache_write":0.0,"max_prompt_cost":0.0049152,"max_completion_cost":0.0117963,"max_cost":0.0127794},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000018846351974469477,"input_cache_write":0.0,"max_prompt_cost":6.175572614994157,"max_completion_cost":14.821148119762283,"max_cost":16.056338028169012},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/voxtral-small-24b-2507","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m2","name":"MiniMax: MiniMax M2","created":1761252093,"description":"MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.825e-7,"completion":1.53e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":5.625e-7,"max_prompt_cost":0.078336,"max_completion_cost":0.20054016,"max_cost":0.22874112},"sats_pricing":{"prompt":0.00048058197534897156,"completion":0.0019223279013958863,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0007067381990426053,"max_prompt_cost":98.42318855146938,"max_completion_cost":251.9633626917616,"max_cost":287.3957105702906},"per_request_limits":null,"top_provider":{"context_length":204800,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m2","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":1.8750000000000003e-6,"max_prompt_cost":0.3,"max_completion_cost":0.4800000000000001,"max_cost":0.6840000000000002},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0023557939968086848,"max_prompt_cost":376.9270394893895,"max_completion_cost":603.0832631830233,"max_cost":859.3936500358083},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","created":1760547638,"description":"Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":9.375000000000001e-7,"max_prompt_cost":0.15,"max_completion_cost":0.24000000000000005,"max_cost":0.3420000000000001},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0011778969984043424,"max_prompt_cost":188.46351974469474,"max_completion_cost":301.54163159151165,"max_cost":429.69682501790413},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-haiku-20251001","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","created":1760463308,"description":"Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.75e-7,"completion":1.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.7999999999999997e-7,"input_cache_write":0.0,"max_prompt_cost":0.098304,"max_completion_cost":0.265420125,"max_cost":0.27525075},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.0014134763980852105,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00022615622369363367,"input_cache_write":0.0,"max_prompt_cost":123.51145229988315,"max_completion_cost":333.48007312384567,"max_cost":345.83150104911357},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-8b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-2.5-flash-image","name":"Google: Nano Banana (Gemini 2.5 Flash Image)","created":1759870431,"description":"Gemini 2.5 Flash Image, a.k.a. \"Nano Banana,\" is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...","context_length":32768,"architecture":{"modality":"text+image->text+image","input_modalities":["image","text"],"output_modalities":["image","text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":4.5e-7,"image_output":0.000045,"web_search":0.021,"internal_reasoning":3.7500000000000005e-6,"input_cache_read":4.499999999999999e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.0147456,"max_completion_cost":0.030720000000000004,"max_cost":0.0417792},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0005653905592340842,"image_output":0.056539055923408424,"web_search":26.384892764257266,"internal_reasoning":0.0047115879936173695,"input_cache_read":0.000056539055923408416,"input_cache_write":0.00015705293312057888,"max_prompt_cost":18.52671784498247,"max_completion_cost":38.59732884371349,"max_cost":52.49236722745034},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-image","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","created":1759794479,"description":"Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.3499999999999996e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.11403263999999999,"max_completion_cost":0.3538935,"max_cost":0.36529702500000005},"sats_pricing":{"prompt":0.0005465442072596147,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":143.27328466786443,"max_completion_cost":444.6400974984609,"max_cost":458.96775389177174},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-thinking","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","created":1759794476,"description":"Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-following for general multimodal tasks. It excels in perception...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.0147456,"max_cost":0.0700416},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":18.52671784498247,"max_cost":88.00190976366673},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-30b-a3b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.6","name":"Z.ai: GLM 4.6","created":1759235576,"description":"Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...","context_length":204800,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.5e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.152064,"max_completion_cost":0.393216,"max_cost":0.44697600000000004},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":191.05677777638175,"max_completion_cost":494.0458091995326,"max_cost":561.5911346760312},"per_request_limits":null,"top_provider":{"context_length":202752,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.6","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":4.5e-7,"input_cache_write":5.625e-6,"max_prompt_cost":4.5,"max_completion_cost":1.4400000000000002,"max_cost":5.652},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0005653905592340842,"input_cache_write":0.007067381990426053,"max_prompt_cost":5653.905592340842,"max_completion_cost":1809.2497895490696,"max_cost":7101.305423980098},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","created":1759161676,"description":"Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...","context_length":1000000,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":2.25e-6,"completion":0.00001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":2.8125e-6,"max_prompt_cost":2.25,"max_completion_cost":0.7200000000000001,"max_cost":2.826},"sats_pricing":{"prompt":0.002826952796170421,"completion":0.014134763980852106,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0035336909952130265,"max_prompt_cost":2826.952796170421,"max_completion_cost":904.6248947745348,"max_cost":3550.652711990049},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":64000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.5-sonnet-20250929","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","created":1759150481,"description":"DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":4.0500000000000004e-7,"completion":6.15e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0663552,"max_completion_cost":0.09068544,"max_cost":0.09732096000000001},"sats_pricing":{"prompt":0.0005088515033106758,"completion":0.0007727004309532485,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":83.37023030242112,"max_completion_cost":113.93931474664221,"max_cost":122.27633777688433},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.2-exp","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","created":1758931878,"description":"Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.088473,"max_cost":0.0943716},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0002826952796170421,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":111.15955321581585,"max_cost":118.57069266625624},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/cydonia-24b-v4.1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"relace-apply-3","name":"Relace: Relace Apply 3","created":1758891572,"description":"Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.275e-6,"completion":1.8750000000000003e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3264,"max_completion_cost":0.24000000000000005,"max_cost":0.40320000000000006},"sats_pricing":{"prompt":0.0016019399178299053,"completion":0.0023557939968086848,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":410.0966189644558,"max_completion_cost":301.54163159151165,"max_cost":506.58994107373957},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"relace/relace-apply-3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","created":1758668687,"description":"Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...","context_length":262144,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":3.15e-7,"completion":2.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.04128768,"max_completion_cost":0.0933888,"max_cost":0.12435456},"sats_pricing":{"prompt":0.000395773391463859,"completion":0.0035808068751492,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":51.874809965950924,"max_completion_cost":117.33587968488898,"max_cost":156.2419871593522},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-vl-235b-a22b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","created":1758548275,"description":"DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":4.0500000000000004e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0663552,"max_completion_cost":0.221184,"max_cost":0.22781952},"sats_pricing":{"prompt":0.0005088515033106758,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":83.37023030242112,"max_completion_cost":277.9007676747371,"max_cost":286.2377907049792},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-v3.1-terminus","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","created":1758115536,"description":"Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via tool calling...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.925e-7,"completion":1.4625e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.85e-8,"input_cache_write":3.65625e-7,"max_prompt_cost":0.2925,"max_completion_cost":0.0958464,"max_cost":0.36917712},"sats_pricing":{"prompt":0.00036750386350215474,"completion":0.0018375193175107737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00007350077270043095,"input_cache_write":0.0004593798293776934,"max_prompt_cost":367.50386350215473,"max_completion_cost":120.42366599238606,"max_cost":463.8427962960636},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-flash","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","created":1757612213,"description":"Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.35e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.03538944,"max_completion_cost":0.0270336,"max_cost":0.060211200000000006},"sats_pricing":{"prompt":0.00016961716777022528,"completion":0.0020730987171916422,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":44.46412282795794,"max_completion_cost":33.965649382467866,"max_cost":75.65076453367844},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-next-80b-a3b-instruct-2509","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","created":1757021147,"description":"Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2359296,"max_completion_cost":0.3686400000000001,"max_cost":0.5160960000000001},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.0047115879936173695,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":296.42748551971954,"max_completion_cost":463.1679461245619,"max_cost":648.4351245743867},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2-0905","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hermes-4-405b","name":"Nous: Hermes 4 405B","created":1756235463,"description":"Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":4.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.530838,"max_cost":0.5505},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":666.9573192948951,"max_cost":691.6611174630297},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"nousresearch/hermes-4-405b","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","created":1755779628,"description":"DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-v3.1"},"pricing":{"prompt":3.75e-7,"completion":1.425e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.9499999999999999e-7,"input_cache_write":0.0,"max_prompt_cost":0.06144,"max_completion_cost":0.2101248,"max_cost":0.2162688},"sats_pricing":{"prompt":0.00047115879936173685,"completion":0.0017904034375746,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00024500257566810316,"input_cache_write":0.0,"max_prompt_cost":77.19465768742697,"max_completion_cost":264.00572929100025,"max_cost":271.72519505974293},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":147456,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3.1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","created":1755095639,"description":"Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":6e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.314571,"max_cost":0.3303},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":395.2343857973891,"max_cost":414.9966704778178},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3.1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.5v","name":"Z.ai: GLM 4.5V","created":1754922288,"description":"GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters, it achieves state-of-the-art results in video understanding,...","context_length":65536,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":2.7e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.0442368,"max_cost":0.0884736},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.0033923433554045052,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020730987171916422,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":55.580153534947414,"max_cost":111.16030706989483},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5v","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.0000225,"completion":0.0001125,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":2.25e-6,"input_cache_write":0.000028125,"max_prompt_cost":4.5,"max_completion_cost":3.6,"max_cost":7.380000000000001},"sats_pricing":{"prompt":0.028269527961704212,"completion":0.14134763980852105,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.002826952796170421,"input_cache_write":0.03533690995213026,"max_prompt_cost":5653.905592340842,"max_completion_cost":4523.124473872674,"max_cost":9272.405171438983},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","created":1754411591,"description":"Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...","context_length":200000,"architecture":{"modality":"text+image+file->text","input_modalities":["image","text","file"],"output_modalities":["text"],"tokenizer":"Claude","instruct_type":null},"pricing":{"prompt":0.00001125,"completion":0.00005625,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.015,"internal_reasoning":0.0,"input_cache_read":1.125e-6,"input_cache_write":0.0000140625,"max_prompt_cost":2.25,"max_completion_cost":1.8,"max_cost":3.6900000000000004},"sats_pricing":{"prompt":0.014134763980852106,"completion":0.07067381990426053,"request":0.001,"image":0.0,"image_output":0.0,"web_search":18.846351974469474,"internal_reasoning":0.0,"input_cache_read":0.0014134763980852105,"input_cache_write":0.01766845497606513,"max_prompt_cost":2826.952796170421,"max_completion_cost":2261.562236936337,"max_cost":4636.202585719491},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":32000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthropic/claude-4.1-opus-20250805","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"codestral-2508","name":"Mistral: Codestral 2508","created":1754079630,"description":"Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.\n\n[Blog Post](https://mistral.ai/news/codestral-25-08)","context_length":256000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.35e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.499999999999999e-8,"input_cache_write":0.0,"max_prompt_cost":0.1152,"max_completion_cost":0.27648,"max_cost":0.29952},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0016961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000056539055923408416,"input_cache_write":0.0,"max_prompt_cost":144.73998316392556,"max_completion_cost":347.3759595934213,"max_cost":376.32395622620646},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":204800,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-2508","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","created":1753972379,"description":"Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. Built on the...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0589824,"max_completion_cost":0.2123361,"max_cost":0.218234475},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":74.10687137992988,"max_completion_cost":266.78405849907654,"max_cost":274.1949152542373},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-30b-a3b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","created":1753806965,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.10616805,"max_cost":0.1101003},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":133.39202924953827,"max_cost":138.33260041964542},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":235929,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-30b-a3b-instruct-2507","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"glm-4.5","name":"Z.ai: GLM 4.5","created":1753471347,"description":"GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":9e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.1179648,"max_completion_cost":0.3244032,"max_cost":0.3538944},"sats_pricing":{"prompt":0.0011307811184681684,"completion":0.0041461974343832845,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020730987171916422,"input_cache_write":0.0,"max_prompt_cost":148.21374275985977,"max_completion_cost":407.58779258961437,"max_cost":444.6412282795793},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"glm-4.5-air","name":"Z.ai: GLM 4.5 Air","created":1753471258,"description":"GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE) architecture but with a more compact parameter...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.9499999999999999e-7,"completion":1.275e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.025559039999999998,"max_completion_cost":0.1253376,"max_cost":0.13172736},"sats_pricing":{"prompt":0.00024500257566810316,"completion":0.0016019399178299053,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":32.11297759796962,"max_completion_cost":157.477101682351,"max_cost":165.5053460818434},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"z-ai/glm-4.5-air","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","created":1753449557,"description":"Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":6.75e-7,"completion":5.25e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0864,"max_completion_cost":0.086016,"max_cost":0.1613568},"sats_pricing":{"prompt":0.0008480858388511263,"completion":0.006596223191064315,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":108.55498737294418,"max_completion_cost":108.07252076239774,"max_cost":202.73246975160507},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-235b-a22b-thinking-2507","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","created":1753230546,"description":"Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.1179648,"max_completion_cost":0.098304,"max_cost":0.1867776},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":148.21374275985977,"max_completion_cost":123.51145229988315,"max_cost":234.67175936977796},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-coder-480b-a35b-07-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.0192,"max_completion_cost":0.0006144,"max_cost":0.0195072},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":24.123330527320924,"max_completion_cost":0.7719465768742696,"max_cost":24.50930381575806},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance/ui-tars-1.5-7b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","created":1753200276,"description":"Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":6e-7,"request":0.0,"image":1.5e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":6e-7,"input_cache_read":1.5000000000000002e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.1572864,"max_completion_cost":0.039320999999999995,"max_cost":0.18677714999999998},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0007538540789787789,"request":0.001,"image":0.00018846351974469473,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0007538540789787789,"input_cache_read":0.000018846351974469477,"input_cache_write":0.00015705293312057888,"max_prompt_cost":197.61832367981302,"max_completion_cost":49.403827065874275,"max_cost":234.6711939792187},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash-lite","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","created":1753119555,"description":"Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":null},"pricing":{"prompt":2.1e-7,"completion":1.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.5e-8,"input_cache_write":0.0,"max_prompt_cost":0.02752512,"max_completion_cost":0.14155679999999998,"max_cost":0.14430948},"sats_pricing":{"prompt":0.00026384892764257263,"completion":0.0015077081579575578,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009423175987234736,"input_cache_write":0.0,"max_prompt_cost":34.58320664396728,"max_completion_cost":177.85528514530534,"max_cost":181.3138168888442},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-235b-a22b-07-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"kimi-k2","name":"MoonshotAI: Kimi K2 0711","created":1752263252,"description":"Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.550000000000001e-7,"completion":3.45e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.11206656000000001,"max_completion_cost":0.33914880000000003,"max_cost":0.36716544},"sats_pricing":{"prompt":0.0010742420625447602,"completion":0.0043346609541279795,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":140.8030556218668,"max_completion_cost":426.11451043459687,"max_cost":461.3152743400636},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":98304,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"moonshotai/kimi-k2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","created":1752094966,"description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.35e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0384,"max_completion_cost":0.0110592,"max_cost":0.0470016},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0016961716777022526,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":48.24666105464185,"max_completion_cost":13.895038383736853,"max_cost":59.053913130881625},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":8192,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"venice/uncensored","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","created":1751987664,"description":"Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.1e-7,"completion":8.550000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.02752512,"max_completion_cost":0.10085922000000001,"max_cost":0.1036119},"sats_pricing":{"prompt":0.00026384892764257263,"completion":0.0010742420625447602,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":34.58320664396728,"max_completion_cost":126.72189066603009,"max_cost":130.18042240956893},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"tencent/hunyuan-a13b-instruct","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"morph-v3-large","name":"Morph: Morph V3 Large","created":1751910858,"description":"Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.35e-6,"completion":2.85e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3538944,"max_completion_cost":0.3735552,"max_cost":0.5505024},"sats_pricing":{"prompt":0.0016961716777022526,"completion":0.0035808068751492,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":444.6412282795793,"max_completion_cost":469.3435187395559,"max_cost":691.6641328793455},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"morph-v3-fast","name":"Morph: Morph V3 Fast","created":1751910002,"description":"Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code> <update>{edit_snippet}</update>...","context_length":262144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":1.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3145728,"max_completion_cost":0.2359296,"max_cost":0.393216},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.002261562236936337,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":395.23664735962603,"max_completion_cost":296.42748551971954,"max_cost":494.0458091995326},"per_request_limits":null,"top_provider":{"context_length":262144,"max_completion_tokens":131072,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"morph/morph-v3-fast","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","created":1750443016,"description":"Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves accuracy on...","context_length":256000,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.125e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0144,"max_completion_cost":0.0049152,"max_cost":0.017472},"sats_pricing":{"prompt":0.00014134763980852105,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.092497895490695,"max_completion_cost":6.175572614994157,"max_cost":21.952230779862045},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.2-24b-instruct-2506","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-m1","name":"MiniMax: MiniMax M1","created":1750200414,"description":"MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture paired with a custom \"lightning attention\" mechanism, allowing it...","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":3.3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.8250000000000001,"max_completion_cost":0.132,"max_cost":0.924},"sats_pricing":{"prompt":0.0010365493585958211,"completion":0.0041461974343832845,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1036.549358595821,"max_completion_cost":165.84789737533137,"max_cost":1160.9352816273197},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":40000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-m1","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","created":1750172488,"description":"Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["file","image","text","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":4.5e-7,"completion":3.7500000000000005e-6,"request":0.0,"image":4.5e-7,"image_output":0.0,"web_search":0.021,"internal_reasoning":3.7500000000000005e-6,"input_cache_read":4.499999999999999e-8,"input_cache_write":1.2499999999999994e-7,"max_prompt_cost":0.4718592,"max_completion_cost":0.24575625000000004,"max_cost":0.6881247},"sats_pricing":{"prompt":0.0005653905592340842,"completion":0.0047115879936173695,"request":0.001,"image":0.0005653905592340842,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.0047115879936173695,"input_cache_read":0.000056539055923408416,"input_cache_write":0.00015705293312057888,"max_prompt_cost":592.8549710394391,"max_completion_cost":308.7739191617143,"max_cost":864.5760199017477},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65535,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-flash","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","created":1750169544,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio+video->text","input_modalities":["text","image","file","audio","video"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":1.8750000000000003e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000015000000000000002,"input_cache_read":1.875e-7,"input_cache_write":5.625e-7,"max_prompt_cost":1.9660800000000003,"max_completion_cost":0.9830400000000001,"max_cost":2.8262400000000003},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0023557939968086848,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.018846351974469478,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0007067381990426053,"max_prompt_cost":2470.2290459976634,"max_completion_cost":1235.1145229988317,"max_cost":3550.954253621641},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","created":1749137257,"description":"Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...","context_length":1048576,"architecture":{"modality":"text+image+file+audio->text","input_modalities":["file","image","text","audio"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":1.8750000000000003e-6,"completion":0.000015000000000000002,"request":0.0,"image":1.8750000000000003e-6,"image_output":0.0,"web_search":0.021,"internal_reasoning":0.000015000000000000002,"input_cache_read":1.875e-7,"input_cache_write":5.625e-7,"max_prompt_cost":1.9660800000000003,"max_completion_cost":0.9830400000000001,"max_cost":2.8262400000000003},"sats_pricing":{"prompt":0.0023557939968086848,"completion":0.018846351974469478,"request":0.001,"image":0.0023557939968086848,"image_output":0.0,"web_search":26.384892764257266,"internal_reasoning":0.018846351974469478,"input_cache_read":0.00023557939968086843,"input_cache_write":0.0007067381990426053,"max_prompt_cost":2470.2290459976634,"max_completion_cost":1235.1145229988317,"max_cost":3550.954253621641},"per_request_limits":null,"top_provider":{"context_length":1048576,"max_completion_tokens":65536,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-2.5-pro-preview-06-05","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"deepseek-r1-0528","name":"DeepSeek: R1 0528","created":1748455170,"description":"May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":"deepseek-r1"},"pricing":{"prompt":7.5e-7,"completion":3.2250000000000005e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":5.25e-7,"input_cache_write":0.0,"max_prompt_cost":0.12288,"max_completion_cost":0.10567680000000002,"max_cost":0.20398080000000002},"sats_pricing":{"prompt":0.0009423175987234737,"completion":0.004051965674510938,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0006596223191064315,"input_cache_write":0.0,"max_prompt_cost":154.38931537485394,"max_completion_cost":132.7748112223744,"max_cost":256.28626352225757},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-r1-0528","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"mistral-medium-3","name":"Mistral: Mistral Medium 3","created":1746627341,"description":"Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...","context_length":131072,"architecture":{"modality":"text+image+file->text","input_modalities":["text","image","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":6e-7,"completion":3e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.0786432,"max_completion_cost":0.314571,"max_cost":0.3303},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.003769270394893895,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":98.80916183990651,"max_completion_cost":395.2343857973891,"max_cost":414.9966704778178},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-medium-3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","created":1745975193,"description":"Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM...","context_length":163840,"architecture":{"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":2.7e-7,"completion":2.7e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0442368,"max_completion_cost":0.00442368,"max_cost":0.0442368},"sats_pricing":{"prompt":0.00033923433554045057,"completion":0.00033923433554045057,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":55.580153534947414,"max_completion_cost":5.558015353494742,"max_cost":55.580153534947414},"per_request_limits":null,"top_provider":{"context_length":163840,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-guard-4-12b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","created":1745878604,"description":"Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":1.7999999999999997e-7,"completion":7.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007372799999999999,"max_completion_cost":0.012288,"max_cost":0.01671168},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0009423175987234737,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.263358922491234,"max_completion_cost":15.438931537485393,"max_cost":20.996946890980134},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-30b-a3b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false,"default_enabled":true},"image_pricing":null},{"id":"qwen3-14b","name":"Qwen: Qwen3 14B","created":1745876478,"description":"Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":40960,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":1.7999999999999997e-7,"completion":3.5999999999999994e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.007372799999999999,"max_completion_cost":0.005898239999999999,"max_cost":0.010321919999999998},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.00045231244738726733,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.263358922491234,"max_completion_cost":7.410687137992988,"max_cost":12.968702491487727},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-14b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"qwen3-32b","name":"Qwen: Qwen3 32B","created":1745875945,"description":"Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a \"thinking\" mode for...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen3","instruct_type":"qwen3"},"pricing":{"prompt":1.2000000000000002e-7,"completion":4.2e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004915200000000001,"max_completion_cost":0.00688128,"max_cost":0.0098304},"sats_pricing":{"prompt":0.0001507708157957558,"completion":0.0005276978552851453,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.1755726149941585,"max_completion_cost":8.64580166099182,"max_cost":12.351145229988314},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-32b-04-28","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":false},"image_pricing":null},{"id":"llama-4-maverick","name":"Meta: Llama 4 Maverick","created":1743881822,"description":"Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...","context_length":524288,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":5.25e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":2.55e-7,"input_cache_write":0.0,"max_prompt_cost":0.2752512,"max_completion_cost":0.049152,"max_cost":0.30720000000000003},"sats_pricing":{"prompt":0.0006596223191064315,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00032038798356598104,"input_cache_write":0.0,"max_prompt_cost":345.83206643967276,"max_completion_cost":61.75572614994157,"max_cost":385.97328843713484},"per_request_limits":null,"top_provider":{"context_length":524288,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-maverick-17b-128e-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-4-scout","name":"Meta: Llama 4 Scout","created":1743881519,"description":"Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...","context_length":1310720,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Llama4","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":4.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.049152,"max_completion_cost":0.0073728,"max_cost":0.054067199999999996},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0005653905592340842,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":61.75572614994157,"max_completion_cost":9.263358922491236,"max_cost":67.93129876493572},"per_request_limits":null,"top_provider":{"context_length":327680,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-4-scout-17b-16e-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","created":1742824755,"description":"DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":4.3499999999999996e-7,"completion":1.7100000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.65e-7,"input_cache_write":0.0,"max_prompt_cost":0.05567999999999999,"max_completion_cost":0.19699200000000003,"max_cost":0.20256000000000002},"sats_pricing":{"prompt":0.0005465442072596147,"completion":0.0021484841250895203,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00020730987171916422,"input_cache_write":0.0,"max_prompt_cost":69.95765852923068,"max_completion_cost":247.50537121031275,"max_cost":254.5011370632358},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3-0324","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","created":1742238937,"description":"Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art performance in text-based reasoning and...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":5.265e-7,"completion":8.325e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.067392,"max_completion_cost":0.08524799999999999,"max_cost":0.09872639999999999},"sats_pricing":{"prompt":0.0006615069543038785,"completion":0.0010459725345830558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":84.67289015089645,"max_completion_cost":107.10758754130491,"max_cost":124.04216557148419},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-3.1-24b-instruct-2503","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-4b-it","name":"Google: Gemma 3 4B","created":1741905510,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":7.5e-8,"completion":1.5e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.0024576,"max_cost":0.011059199999999998},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.00018846351974469473,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":3.0877863074970784,"max_cost":13.895038383736852},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-4b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-3-12b-it","name":"Google: Gemma 3 12B","created":1741902625,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":7.5e-8,"completion":2.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.0036864,"max_cost":0.012287999999999999},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.0002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":4.631679461245618,"max_cost":15.438931537485391},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-12b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-a","name":"Cohere: Command A","created":1741894342,"description":"Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary...","context_length":256000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9600000000000002,"max_completion_cost":0.12288000000000002,"max_cost":1.0521600000000002},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1206.1665263660466,"max_completion_cost":154.38931537485396,"max_cost":1321.9585128971871},"per_request_limits":null,"top_provider":{"context_length":256000,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-a-03-2025","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"reka-flash-3","name":"Reka Flash 3","created":1741812813,"description":"Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-following, and function calling. Featuring a...","context_length":65536,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.017694599999999998,"max_cost":0.0186777},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":22.231910643163168,"max_cost":23.4671005515699},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"rekaai/reka-flash-3","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"gemma-3-27b-it","name":"Google: Gemma 3 27B","created":1741756359,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...","context_length":131072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":1.2000000000000002e-7,"completion":5.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6.000000000000001e-8,"input_cache_write":0.0,"max_prompt_cost":0.015728640000000002,"max_completion_cost":0.061931099999999996,"max_cost":0.06350406},"sats_pricing":{"prompt":0.0001507708157957558,"completion":0.0006596223191064315,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0000753854078978779,"input_cache_write":0.0,"max_prompt_cost":19.761832367981306,"max_completion_cost":77.81168725107109,"max_cost":79.78799110452186},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-3-27b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","created":1741636566,"description":"Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.25e-7,"completion":1.2e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-7,"input_cache_write":0.0,"max_prompt_cost":0.0270336,"max_completion_cost":0.035389199999999996,"max_cost":0.038092724999999994},"sats_pricing":{"prompt":0.0010365493585958211,"completion":0.0015077081579575578,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00047115879936173685,"input_cache_write":0.0,"max_prompt_cost":33.965649382467866,"max_completion_cost":44.463821286326336,"max_cost":47.86059353444484},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/skyfall-36b-v2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","created":1741313308,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":3e-6,"completion":0.000012,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.384,"max_completion_cost":1.3824,"max_cost":1.4208},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":482.46661054641856,"max_completion_cost":1736.879797967107,"max_cost":1785.1264590217486},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-reasoning-pro","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"sonar-pro","name":"Perplexity: Sonar Pro","created":1741312423,"description":"Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...","context_length":200000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.5e-6,"completion":0.0000225,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.9,"max_completion_cost":0.18000000000000002,"max_cost":1.044},"sats_pricing":{"prompt":0.005653905592340842,"completion":0.028269527961704212,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1130.7811184681684,"max_completion_cost":226.1562236936337,"max_cost":1311.7060974230756},"per_request_limits":null,"top_provider":{"context_length":200000,"max_completion_tokens":8000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-pro","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar-deep-research","name":"Perplexity: Sonar Deep Research","created":1741311246,"description":"Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":"deepseek-r1"},"pricing":{"prompt":3e-6,"completion":0.000012,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":4.5e-6,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.384,"max_completion_cost":1.3824,"max_cost":1.4208},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.01507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.005653905592340842,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":482.46661054641856,"max_completion_cost":1736.879797967107,"max_cost":1785.1264590217486},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar-deep-research","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true},"image_pricing":null},{"id":"mistral-saba","name":"Mistral: Saba","created":1739803239,"description":"Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...","context_length":32768,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.0000000000000004e-8,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.0235926,"max_cost":0.0255588},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00003769270394893895,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":29.642296239524565,"max_cost":32.112676056338024},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":26214,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-saba-2502","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","created":1738696718,"description":"Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":2.4e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.07077839999999999,"max_cost":0.0747108},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.0030154163159151156,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":88.92764257265267,"max_cost":93.8684022062796},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"aion-labs/aion-rp-llama-3.1-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","created":1738410311,"description":"Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.","context_length":128000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":6e-7,"input_cache_write":0.0,"max_prompt_cost":0.1536,"max_completion_cost":0.1728,"max_cost":0.18816},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0007538540789787789,"input_cache_write":0.0,"max_prompt_cost":192.9866442185674,"max_completion_cost":217.10997474588837,"max_cost":236.40863916774506},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":115200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen2.5-vl-72b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-plus","name":"Qwen: Qwen-Plus","created":1738409840,"description":"Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.","context_length":1000000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":3.8999999999999997e-7,"completion":1.17e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":7.800000000000001e-8,"input_cache_write":4.875e-7,"max_prompt_cost":0.38999999999999996,"max_completion_cost":0.03833856,"max_cost":0.41555904},"sats_pricing":{"prompt":0.0004900051513362063,"completion":0.001470015454008619,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00009800103026724128,"input_cache_write":0.0006125064391702579,"max_prompt_cost":490.00515133620627,"max_completion_cost":48.16946639695443,"max_cost":522.118128934176},"per_request_limits":null,"top_provider":{"context_length":1000000,"max_completion_tokens":32768,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-plus-2025-01-25","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","created":1738255409,"description":"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":7.5e-8,"completion":1.2000000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0024576,"max_completion_cost":0.0019660800000000003,"max_cost":0.00319488},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.0001507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.0877863074970784,"max_completion_cost":2.4702290459976632,"max_cost":4.014122199746202},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-small-24b-instruct-2501","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"sonar","name":"Perplexity: Sonar","created":1738013808,"description":"Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...","context_length":127072,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-6,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0075,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.190608,"max_completion_cost":0.171546,"max_cost":0.190608},"sats_pricing":{"prompt":0.0018846351974469474,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":9.423175987234737,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":239.4843638099785,"max_completion_cost":215.5344197208227,"max_cost":239.4843638099785},"per_request_limits":null,"top_provider":{"context_length":127072,"max_completion_tokens":114364,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/sonar","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"minimax-01","name":"MiniMax: MiniMax-01","created":1736915462,"description":"MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a context...","context_length":1000192,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3e-7,"completion":1.65e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3000576,"max_completion_cost":1.4852838000000002,"max_cost":1.5152898000000001},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0020730987171916422,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":376.9994094809714,"max_completion_cost":1866.1454184518352,"max_cost":1903.845660941564},"per_request_limits":null,"top_provider":{"context_length":1000192,"max_completion_tokens":900172,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"minimax/minimax-01","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"phi-4","name":"Microsoft: Phi 4","created":1736489872,"description":"[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...","context_length":16384,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.05e-7,"completion":2.1e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00172032,"max_completion_cost":0.00309645,"max_cost":0.0032685450000000003},"sats_pricing":{"prompt":0.00013192446382128632,"completion":0.00026384892764257263,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.161450415247955,"max_completion_cost":3.8904524380897336,"max_cost":4.106676634292822},"per_request_limits":null,"top_provider":{"context_length":16384,"max_completion_tokens":14745,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"microsoft/phi-4","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"deepseek-chat","name":"DeepSeek: DeepSeek V3","created":1735241320,"description":"DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...","context_length":163840,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"DeepSeek","instruct_type":null},"pricing":{"prompt":3.861e-7,"completion":1.54305e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":4.2e-8,"input_cache_write":0.0,"max_prompt_cost":0.0494208,"max_completion_cost":0.0246888,"max_cost":0.067932},"sats_pricing":{"prompt":0.00048510509982284427,"completion":0.0019387242276136748,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.000052769785528514525,"input_cache_write":0.0,"max_prompt_cost":62.09345277732407,"max_completion_cost":31.0195876418188,"max_cost":85.35135882197736},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":16000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"deepseek/deepseek-chat-v3","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","created":1734158152,"description":"Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":5.625e-8,"completion":2.25e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0072,"max_completion_cost":0.0009,"max_cost":0.007875},"sats_pricing":{"prompt":0.00007067381990426053,"completion":0.0002826952796170421,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":9.046248947745347,"max_completion_cost":1.1307811184681684,"max_cost":9.894334786596474},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r7b-12-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","created":1733506137,"description":"The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":3e-7,"completion":7.799999999999999e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":1.5e-7,"input_cache_write":0.0,"max_prompt_cost":0.0393216,"max_completion_cost":0.09984,"max_cost":0.10076159999999999},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0009800103026724126,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00018846351974469473,"input_cache_write":0.0,"max_prompt_cost":49.404580919953254,"max_completion_cost":125.44131874206882,"max_cost":126.59923860738022},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":128000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.3-70b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-lite-v1","name":"Amazon: Nova Lite 1.0","created":1733437363,"description":"Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":8.999999999999999e-8,"completion":3.5999999999999994e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.026999999999999996,"max_completion_cost":0.0018431999999999997,"max_cost":0.028382399999999995},"sats_pricing":{"prompt":0.00011307811184681683,"completion":0.00045231244738726733,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":33.92343355404505,"max_completion_cost":2.3158397306228085,"max_cost":35.66031335201215},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-lite-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-micro-v1","name":"Amazon: Nova Micro 1.0","created":1733437237,"description":"Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":5.25e-8,"completion":2.1e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00672,"max_completion_cost":0.0010752000000000001,"max_cost":0.0075264},"sats_pricing":{"prompt":0.00006596223191064316,"completion":0.00026384892764257263,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":8.443165684562326,"max_completion_cost":1.3509065095299722,"max_cost":9.456345566709803},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-micro-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"nova-pro-v1","name":"Amazon: Nova Pro 1.0","created":1733436303,"description":"Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...","context_length":300000,"architecture":{"modality":"text+image->text","input_modalities":["text","image"],"output_modalities":["text"],"tokenizer":"Nova","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":4.8e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.36,"max_completion_cost":0.024576,"max_cost":0.378432},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.006030832631830231,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":452.31244738726735,"max_completion_cost":30.877863074970787,"max_cost":475.47084469349545},"per_request_limits":null,"top_provider":{"context_length":300000,"max_completion_tokens":5120,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/nova-pro-v1","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large-2407","name":"Mistral Large 2407","created":1731978415,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":131072,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.393216,"max_completion_cost":0.943713,"max_cost":1.022358},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":494.0458091995326,"max_completion_cost":1185.7031573921674,"max_cost":1284.5145807943109},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":104857,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large-2407","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","created":1731368400,"description":"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":9.9e-7,"completion":1.5e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.03244032,"max_completion_cost":0.0442365,"max_cost":0.04748073},"sats_pricing":{"prompt":0.0012438592303149853,"completion":0.0018846351974469474,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":40.75877925896144,"max_completion_cost":55.579776607907924,"max_cost":59.655903305650135},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-coder-32b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","created":1731103448,"description":"UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.","context_length":1024000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":6e-7,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6144,"max_completion_cost":0.49151999999999996,"max_cost":0.6144},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":771.9465768742696,"max_completion_cost":617.5572614994156,"max_cost":771.9465768742696},"per_request_limits":null,"top_provider":{"context_length":1024000,"max_completion_tokens":819200,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thedrummer/unslopnemo-12b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"magnum-v4-72b","name":"Magnum v4 72B","created":1729555200,"description":"This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).\n\nThe model is fine-tuned on top of [Qwen2.5 72B](https://openrouter.ai/qwen/qwen-2.5-72b-instruct).","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":3.7500000000000005e-6,"completion":7.500000000000001e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.12288000000000002,"max_completion_cost":0.030720000000000004,"max_cost":0.13824000000000003},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.009423175987234739,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":154.38931537485396,"max_completion_cost":38.59732884371349,"max_cost":173.68797979671072},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":4096,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"anthracite-org/magnum-v4-72b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","created":1729036800,"description":"Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":1.5e-7,"completion":3e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0049152,"max_completion_cost":0.008847299999999999,"max_cost":0.00933885},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.00037692703948938945,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.175572614994157,"max_completion_cost":11.115955321581584,"max_cost":11.73355027578495},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-7b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","created":1727222400,"description":"Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...","context_length":60000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":4.05e-8,"completion":3.015e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00243,"max_completion_cost":0.016281,"max_cost":0.016524},"sats_pricing":{"prompt":0.00005088515033106758,"completion":0.0003788116746868364,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.0531090198640545,"max_completion_cost":20.45583043308917,"max_cost":20.761141335075575},"per_request_limits":null,"top_provider":{"context_length":60000,"max_completion_tokens":54000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.2-1b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","created":1727222400,"description":"Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":7.634999999999999e-8,"completion":5.025000000000001e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.006108,"max_completion_cost":0.036180000000000004,"max_cost":0.036790800000000005},"sats_pricing":{"prompt":0.00009592793155004961,"completion":0.0006313527911447275,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.674234524003969,"max_completion_cost":45.45740096242038,"max_cost":46.22482441482077},"per_request_limits":null,"top_provider":{"context_length":80000,"max_completion_tokens":72000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.2-3b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","created":1726704000,"description":"Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...","context_length":32768,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Qwen","instruct_type":"chatml"},"pricing":{"prompt":5.4e-7,"completion":6e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.01769472,"max_completion_cost":0.0098304,"max_cost":0.01867776},"sats_pricing":{"prompt":0.0006784686710809011,"completion":0.0007538540789787789,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":22.23206141397897,"max_completion_cost":12.351145229988314,"max_cost":23.4671759369778},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-2.5-72b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r-08-2024","name":"Cohere: Command R (08-2024)","created":1724976000,"description":"command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":9e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0288,"max_completion_cost":0.0036,"max_cost":0.0315},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":36.18499579098139,"max_completion_cost":4.523124473872674,"max_cost":39.577339146385896},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-08-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","created":1724976000,"description":"command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...","context_length":128000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":3.7500000000000005e-6,"completion":0.000015000000000000002,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.4800000000000001,"max_completion_cost":0.06000000000000001,"max_cost":0.5250000000000001},"sats_pricing":{"prompt":0.0047115879936173695,"completion":0.018846351974469478,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":603.0832631830233,"max_completion_cost":75.38540789787791,"max_cost":659.6223191064317},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":4000,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/command-r-plus-08-2024","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","created":1724803200,"description":"Euryale L3.1 70B v2.2 is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.1](/models/sao10k/l3-euryale-70b).","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":1.275e-6,"completion":1.275e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1671168,"max_completion_cost":0.0208896,"max_cost":0.1671168},"sats_pricing":{"prompt":0.0016019399178299053,"completion":0.0016019399178299053,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":209.96946890980135,"max_completion_cost":26.24618361372517,"max_cost":209.96946890980135},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3.1-euryale-70b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","created":1723507200,"description":"Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":6.000000000000001e-8,"completion":7.5e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0004915200000000001,"max_completion_cost":0.0005528999999999999,"max_cost":0.0006020999999999999},"sats_pricing":{"prompt":0.0000753854078978779,"completion":0.00009423175987234736,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6175572614994158,"max_completion_cost":0.6946765337789448,"max_cost":0.7564925682552046},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":7372,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sao10k/l3-lunaris-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":1.08e-6,"completion":1.08e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.14155776,"max_completion_cost":0.00884736,"max_cost":0.14155776},"sats_pricing":{"prompt":0.0013569373421618023,"completion":0.0013569373421618023,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":177.85649131183175,"max_completion_cost":11.116030706989484,"max_cost":177.85649131183175},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":8192,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-70b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","created":1721692800,"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama3","instruct_type":"llama3"},"pricing":{"prompt":7.5e-8,"completion":1.2000000000000002e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3.75e-8,"input_cache_write":0.0,"max_prompt_cost":0.0098304,"max_completion_cost":0.014155680000000002,"max_cost":0.015138780000000003},"sats_pricing":{"prompt":0.00009423175987234736,"completion":0.0001507708157957558,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00004711587993617368,"input_cache_write":0.0,"max_prompt_cost":12.351145229988314,"max_completion_cost":17.78552851453054,"max_cost":19.020718422937268},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":117964,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"meta-llama/llama-3.1-8b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-nemo","name":"Mistral: Mistral Nemo","created":1721347200,"description":"A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...","context_length":131072,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":4.35e-8,"completion":4.499999999999999e-8,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.005701632,"max_completion_cost":0.0007372799999999999,"max_cost":0.005726208},"sats_pricing":{"prompt":0.00005465442072596147,"completion":0.000056539055923408416,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.163664233393222,"max_completion_cost":0.9263358922491235,"max_cost":7.194542096468194},"per_request_limits":null,"top_provider":{"context_length":131072,"max_completion_tokens":16384,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-nemo","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemma-2-27b-it","name":"Google: Gemma 2 27B","created":1720828800,"description":"Gemma 2 27B by Google is an open model built from the same research and technology used to create the [Gemini models](/models?q=gemini). Gemma models are well-suited for a variety of...","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Gemini","instruct_type":"gemma"},"pricing":{"prompt":9.75e-7,"completion":9.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0079872,"max_completion_cost":0.0019968,"max_cost":0.0079872},"sats_pricing":{"prompt":0.0012250128783405157,"completion":0.0012250128783405157,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":10.035305499365505,"max_completion_cost":2.508826374841376,"max_cost":10.035305499365505},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":2048,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemma-2-27b-it","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","created":1713312000,"description":"Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,...","context_length":65536,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":"mistral"},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.196608,"max_completion_cost":0.471852,"max_cost":0.511176},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":247.0229045997663,"max_completion_cost":592.8459247904914,"max_cost":642.2535211267605},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":52428,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mixtral-8x22b-instruct","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-large","name":"Mistral Large","created":1708905600,"description":"This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....","context_length":128000,"architecture":{"modality":"text+file->text","input_modalities":["text","file"],"output_modalities":["text"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":3e-6,"completion":9e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":3e-7,"input_cache_write":0.0,"max_prompt_cost":0.384,"max_completion_cost":0.9216,"max_cost":0.9984},"sats_pricing":{"prompt":0.003769270394893895,"completion":0.011307811184681684,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.00037692703948938945,"input_cache_write":0.0,"max_prompt_cost":482.46661054641856,"max_completion_cost":1157.9198653114045,"max_cost":1254.4131874206882},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":102400,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-large","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"weaver","name":"Mancer: Weaver (alpha)","created":1690934400,"description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","context_length":8000,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":6e-7,"completion":1.125e-6,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0048,"max_completion_cost":0.00675,"max_cost":0.00795},"sats_pricing":{"prompt":0.0007538540789787789,"completion":0.0014134763980852105,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":6.030832631830231,"max_completion_cost":8.480858388511264,"max_cost":9.988566546468823},"per_request_limits":null,"top_provider":{"context_length":8000,"max_completion_tokens":6000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mancer/weaver","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"remm-slerp-l2-13b","name":"ReMM SLERP 13B","created":1689984000,"description":"A recreation trial of the original MythoMax-L2-B13 but with updated models. #merge","context_length":6144,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":5.25e-7,"completion":9.75e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0032255999999999995,"max_completion_cost":0.0053907749999999996,"max_cost":0.00571365},"sats_pricing":{"prompt":0.0006596223191064315,"completion":0.0012250128783405157,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":4.052719528589915,"max_completion_cost":6.773096204344712,"max_cost":7.178763930595167},"per_request_limits":null,"top_provider":{"context_length":6144,"max_completion_tokens":5529,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"undi95/remm-slerp-l2-13b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mythomax-l2-13b","name":"MythoMax 13B","created":1688256000,"description":"One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay. #merge","context_length":8192,"architecture":{"modality":"text->text","input_modalities":["text"],"output_modalities":["text"],"tokenizer":"Llama2","instruct_type":"alpaca"},"pricing":{"prompt":1.2000000000000002e-7,"completion":1.65e-7,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0004915200000000001,"max_completion_cost":0.00060819,"max_cost":0.00065739},"sats_pricing":{"prompt":0.0001507708157957558,"completion":0.00020730987171916422,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.6175572614994158,"max_completion_cost":0.7641441871568393,"max_cost":0.8259602216330991},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"gryphe/mythomax-l2-13b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"embed-5-fast","name":"Cohere: Embed 5 Fast","created":1793739025,"description":"Embed 5 Fast is the lower-latency, cost-efficient tier of Cohere's Embed 5 family of multimodal embedding models (about 1B parameters). It embeds text, images, and interleaved text and image content...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.2000000000000002e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.015360000000000002,"max_completion_cost":0.0,"max_cost":0.015360000000000002},"sats_pricing":{"prompt":0.0001507708157957558,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":19.298664421856746,"max_completion_cost":0.0,"max_cost":19.298664421856746},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-fast-20261029","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"embed-5-pro","name":"Cohere: Embed 5 Pro","created":1793739016,"description":"Embed 5 Pro is the higher-accuracy tier of Cohere's Embed 5 family of multimodal embedding models (about 2.4B parameters). It embeds text, images, and interleaved text and image content into...","context_length":128000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Cohere","instruct_type":null},"pricing":{"prompt":1.7999999999999997e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.023039999999999998,"max_completion_cost":0.0,"max_cost":0.023039999999999998},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":28.94799663278511,"max_completion_cost":0.0,"max_cost":28.94799663278511},"per_request_limits":null,"top_provider":{"context_length":128000,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"cohere/embed-5-pro-20261029","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-image-v1","name":"Amazon: Titan Multimodal Embeddings G1","created":1793044729,"description":"Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. Images are sent as base64 (up to...","context_length":128,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.2e-6,"completion":0.0,"request":0.0,"image":0.00009,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0001536,"max_completion_cost":0.0,"max_cost":0.0001536},"sats_pricing":{"prompt":0.0015077081579575578,"completion":0.0,"request":0.001,"image":0.11307811184681685,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1929866442185674,"max_completion_cost":0.0,"max_cost":0.1929866442185674},"per_request_limits":null,"top_provider":{"context_length":128,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-image-v1-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-text-v1","name":"Amazon: Titan Embeddings G1 - Text","created":1793044727,"description":"Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. It accepts up to 8,192 tokens per input and returns fixed 1,536-dimension vectors; the `dimensions` parameter is...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0012288,"max_completion_cost":0.0,"max_cost":0.0012288},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.5438931537485392,"max_completion_cost":0.0,"max_cost":1.5438931537485392},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v1-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"titan-embed-text-v2","name":"Amazon: Titan Text Embeddings V2","created":1793044722,"description":"Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. It accepts up to 8,192 tokens per input and returns normalized vectors of 1,024 dimensions...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.0000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00024576000000000003,"max_completion_cost":0.0,"max_cost":0.00024576000000000003},"sats_pricing":{"prompt":0.00003769270394893895,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.3087786307497079,"max_completion_cost":0.0,"max_cost":0.3087786307497079},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":true},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"amazon/titan-embed-text-v2-20261026","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-code-4","name":"VoyageAI by MongoDB: voyage-code-4","created":1786636912,"description":"voyage-code-4 is a code embedding model from Voyage AI, a MongoDB company. It is designed for coding agents and code retrieval, with Matryoshka embeddings at 2048t voyage-code-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.7999999999999997e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0057599999999999995,"max_completion_cost":0.0,"max_cost":0.0057599999999999995},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.236999158196277,"max_completion_cost":0.0,"max_cost":7.236999158196277},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-code-4-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-multimodal-3.5","name":"VoyageAI by MongoDB: voyage-multimodal-3.5","created":1785188629,"description":"voyage-multimodal-3.5 is a state-of-the-art multimodal embedding model capable of vectorizing not only text, images, and video individually, but also content that interleaves all three modalities. It delivers excellent performance for...","context_length":32000,"architecture":{"modality":"text+image->embeddings","input_modalities":["text","image"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.7999999999999997e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0057599999999999995,"max_completion_cost":0.0,"max_cost":0.0057599999999999995},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.236999158196277,"max_completion_cost":0.0,"max_cost":7.236999158196277},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-multimodal-3.5-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4-lite","name":"VoyageAI by MongoDB: voyage-4-lite","created":1785188627,"description":"voyage-4-lite is a lightweight, general-purpose embedding model optimized for low latency and cost. Enabled by Matryoshka learning and quantization-aware training, voyage-4-lite supports embeddings t voyage-4-lite here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.0000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0009600000000000001,"max_completion_cost":0.0,"max_cost":0.0009600000000000001},"sats_pricing":{"prompt":0.00003769270394893895,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.2061665263660466,"max_completion_cost":0.0,"max_cost":1.2061665263660466},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-lite-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4","name":"VoyageAI by MongoDB: voyage-4","created":1785188626,"description":"voyage-4 is a general-purpose (including multilingual) embedding model optimized for retrieval/search and AI applications. voyage-4 supports embedd about voyage-4 here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":8.999999999999999e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0028799999999999997,"max_completion_cost":0.0,"max_cost":0.0028799999999999997},"sats_pricing":{"prompt":0.00011307811184681683,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.6184995790981387,"max_completion_cost":0.0,"max_cost":3.6184995790981387},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"voyage-4-large","name":"VoyageAI by MongoDB: voyage-4-large","created":1785188624,"description":"voyage-4-large is a state-of-the-art general-purpose and multilingual embedding optimized for retrieval quality. Enabled by Matryoshka learning and quantization-aware training, voyage-4-large supports embeddings  voyage-4-large here: [mongodb.com/products/platform/ai-search-and-retrieval/models](https://www.mongodb.com/products/platform/ai-search-and-retrieval/models?utm_source=openrouter&utm_medium=referral)","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.7999999999999997e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0057599999999999995,"max_completion_cost":0.0,"max_cost":0.0057599999999999995},"sats_pricing":{"prompt":0.00022615622369363367,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.236999158196277,"max_completion_cost":0.0,"max_cost":7.236999158196277},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"voyageai/voyage-4-large-20260727","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-2","name":"Google: Gemini Embedding 2","created":1779290135,"description":"Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-7,"completion":0.0,"request":0.0,"image":6.75e-7,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0024576,"max_completion_cost":0.0,"max_cost":0.0024576},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0,"request":0.001,"image":0.0008480858388511263,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.0877863074970784,"max_completion_cost":0.0,"max_cost":3.0877863074970784},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-2-preview","name":"Google: Gemini Embedding 2 Preview","created":1776436465,"description":"Gemini Embedding 2 Preview is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It...","context_length":8192,"architecture":{"modality":"text+image+file+audio+video->embeddings","input_modalities":["text","image","file","audio","video"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":3e-7,"completion":0.0,"request":0.0,"image":6.75e-7,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0024576,"max_completion_cost":0.0,"max_cost":0.0024576},"sats_pricing":{"prompt":0.00037692703948938945,"completion":0.0,"request":0.001,"image":0.0008480858388511263,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.0877863074970784,"max_completion_cost":0.0,"max_cost":3.0877863074970784},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-2-preview","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pplx-embed-v1-4b","name":"Perplexity: Embed V1 4B","created":1773625372,"description":"pplx-embed-v1 -4B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 4B parameter model maximizing retrieval...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":4.499999999999999e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0014399999999999999,"max_completion_cost":0.0,"max_cost":0.0014399999999999999},"sats_pricing":{"prompt":0.000056539055923408416,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.8092497895490693,"max_completion_cost":0.0,"max_cost":1.8092497895490693},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-4B","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"pplx-embed-v1-0.6b","name":"Perplexity: Embed V1 0.6B","created":1773624868,"description":"pplx-embed-v1-0.6B is one of Perplexity's state-of-the-art text embedding models built for real-world, web-scale retrieval. pplx-embed-v1 is optimized for standard dense text retrieval with the 0.6B parameter model targeting lightweight, low-latency...","context_length":32000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":6.000000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00019200000000000003,"max_completion_cost":0.0,"max_cost":0.00019200000000000003},"sats_pricing":{"prompt":7.538540789787791e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.2412333052732093,"max_completion_cost":0.0,"max_cost":0.2412333052732093},"per_request_limits":null,"top_provider":{"context_length":32000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"perplexity/pplx-embed-v1-0.6B","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gte-base","name":"Thenlper: GTE-Base","created":1763433820,"description":"The gte-base embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, delivering efficient and effective semantic embeddings optimized for textual similarity, semantic search, and clustering applications.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-base-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gte-large","name":"Thenlper: GTE-Large","created":1763433655,"description":"The gte-large embedding model converts English sentences, paragraphs and moderate-length documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for information retrieval, semantic textual similarity, reranking and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.680000000000001e-6,"max_completion_cost":0.0,"max_cost":7.680000000000001e-6},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.009649332210928372,"max_completion_cost":0.0,"max_cost":0.009649332210928372},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"thenlper/gte-large-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e5-large-v2","name":"Intfloat: E5-Large-v2","created":1763433432,"description":"The e5-large-v2 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-accuracy semantic embeddings optimized for retrieval, semantic search, reranking, and similarity-scoring tasks.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.680000000000001e-6,"max_completion_cost":0.0,"max_cost":7.680000000000001e-6},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.009649332210928372,"max_completion_cost":0.0,"max_cost":0.009649332210928372},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-large-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"e5-base-v2","name":"Intfloat: E5-Base-v2","created":1763433192,"description":"The e5-base-v2 embedding model encodes English sentences and paragraphs into a 768-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, similarity scoring,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/e5-base-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"multilingual-e5-large","name":"Intfloat: Multilingual-E5-Large","created":1763433047,"description":"The multilingual-e5-large embedding model encodes sentences, paragraphs, and documents across over 90 languages into a 1024-dimensional dense vector space, delivering robust semantic embeddings optimized for multilingual retrieval, cross-language similarity, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.680000000000001e-6,"max_completion_cost":0.0,"max_cost":7.680000000000001e-6},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.009649332210928372,"max_completion_cost":0.0,"max_cost":0.009649332210928372},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"intfloat/multilingual-e5-large-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"paraphrase-minilm-l6-v2","name":"Sentence Transformers: paraphrase-MiniLM-L6-v2","created":1763432454,"description":"The paraphrase-MiniLM-L6-v2 embedding model converts sentences and short paragraphs into a 384-dimensional dense vector space, producing high-quality semantic embeddings optimized for paraphrase detection, semantic similarity scoring, clustering, and lightweight retrieval...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/paraphrase-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-minilm-l12-v2","name":"Sentence Transformers: all-MiniLM-L12-v2","created":1763432155,"description":"The all-MiniLM-L12-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, producing efficient and high-quality semantic embeddings optimized for tasks such as semantic search, clustering, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l12-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-base-en-v1.5","name":"BAAI: bge-base-en-v1.5","created":1763431837,"description":"The bge-base-en-v1.5 embedding model converts English sentences and paragraphs into 768-dimensional dense vectors, delivering efficient, high-quality semantic embeddings optimized for retrieval, semantic search, and document-matching workflows. This version (v1.5) features...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-base-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"multi-qa-mpnet-base-dot-v1","name":"Sentence Transformers: multi-qa-mpnet-base-dot-v1","created":1763431339,"description":"The multi-qa-mpnet-base-dot-v1 embedding model transforms sentences and short paragraphs into a 768-dimensional dense vector space, generating high-quality semantic embeddings optimized for question-and-answer retrieval, semantic search, and similarity-scoring across diverse content.","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/multi-qa-mpnet-base-dot-v1-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-large-en-v1.5","name":"BAAI: bge-large-en-v1.5","created":1763431087,"description":"The bge-large-en-v1.5 embedding model maps English sentences, paragraphs, and documents into a 1024-dimensional dense vector space, delivering high-fidelity semantic embeddings optimized for semantic search, document retrieval, and downstream NLP tasks...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":7.680000000000001e-6,"max_completion_cost":0.0,"max_cost":7.680000000000001e-6},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.009649332210928372,"max_completion_cost":0.0,"max_cost":0.009649332210928372},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-large-en-v1.5-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"bge-m3","name":"BAAI: bge-m3","created":1763424372,"description":"The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.","context_length":8194,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.00012291000000000003,"max_completion_cost":0.0,"max_cost":0.00012291000000000003},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.1544270080788029,"max_completion_cost":0.0,"max_cost":0.1544270080788029},"per_request_limits":null,"top_provider":{"context_length":8194,"max_completion_tokens":8194,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"baai/bge-m3-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-mpnet-base-v2","name":"Sentence Transformers: all-mpnet-base-v2","created":1763421830,"description":"The all-mpnet-base-v2 embedding model encodes sentences and short paragraphs into a 768-dimensional dense vector space, providing high-fidelity semantic embeddings well suited for tasks like information retrieval, clustering, similarity scoring, and...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-mpnet-base-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"all-minilm-l6-v2","name":"Sentence Transformers: all-MiniLM-L6-v2","created":1763421176,"description":"The all-MiniLM-L6-v2 embedding model maps sentences and short paragraphs into a 384-dimensional dense vector space, enabling high-quality semantic representations that are ideal for downstream tasks such as information retrieval, clustering,...","context_length":512,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":7.500000000000001e-9,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":3.8400000000000005e-6,"max_completion_cost":0.0,"max_cost":3.8400000000000005e-6},"sats_pricing":{"prompt":9.423175987234738e-6,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.004824666105464186,"max_completion_cost":0.0,"max_cost":0.004824666105464186},"per_request_limits":null,"top_provider":{"context_length":512,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sentence-transformers/all-minilm-l6-v2-20251117","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"mistral-embed-2312","name":"Mistral: Mistral Embed 2312","created":1761944622,"description":"Mistral Embed is a specialized embedding model for text data, optimized for semantic search and RAG applications. Developed by Mistral AI in late 2023, it produces 1024-dimensional vectors that effectively...","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":1.5e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0012288,"max_completion_cost":0.0,"max_cost":0.0012288},"sats_pricing":{"prompt":0.00018846351974469473,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.5438931537485392,"max_completion_cost":0.0,"max_cost":1.5438931537485392},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/mistral-embed-2312","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"gemini-embedding-001","name":"Google: Gemini Embedding 001","created":1761943410,"description":"gemini-embedding-001 provides a unified cutting edge experience across domains, including science, legal, finance, and coding. This embedding model has consistently held a top spot on the Massive Text Embedding Benchmark...","context_length":20000,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Gemini","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045,"max_completion_cost":0.0,"max_cost":0.0045},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.653905592340842,"max_completion_cost":0.0,"max_cost":5.653905592340842},"per_request_limits":null,"top_provider":{"context_length":20000,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"google/gemini-embedding-001","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"codestral-embed-2505","name":"Mistral: Codestral Embed 2505","created":1761864460,"description":"Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.","context_length":8192,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Mistral","instruct_type":null},"pricing":{"prompt":2.25e-7,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0018432,"max_completion_cost":0.0,"max_cost":0.0018432},"sats_pricing":{"prompt":0.0002826952796170421,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":2.315839730622809,"max_completion_cost":0.0,"max_cost":2.315839730622809},"per_request_limits":null,"top_provider":{"context_length":8192,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"mistralai/codestral-embed-2505","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-embedding-8b","name":"Qwen: Qwen3 Embedding 8B","created":1761680622,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":40960,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":1.5000000000000002e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0006144000000000001,"max_completion_cost":0.0,"max_cost":0.00013440000000000001},"sats_pricing":{"prompt":0.000018846351974469477,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.7719465768742698,"max_completion_cost":0.0,"max_cost":0.16886331369124652},"per_request_limits":null,"top_provider":{"context_length":40960,"max_completion_tokens":32000,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-8b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"qwen3-embedding-4b","name":"Qwen: Qwen3 Embedding 4B","created":1761662922,"description":"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text...","context_length":32768,"architecture":{"modality":"text->embeddings","input_modalities":["text"],"output_modalities":["embeddings"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":3.0000000000000004e-8,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0009830400000000001,"max_completion_cost":0.0,"max_cost":0.0009830400000000001},"sats_pricing":{"prompt":0.00003769270394893895,"completion":0.0,"request":0.001,"image":0.0,"image_output":0.0,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":1.2351145229988316,"max_completion_cost":0.0,"max_cost":1.2351145229988316},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":null,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen3-embedding-4b","alias_ids":null,"forwarded_model_id":null,"image_pricing":null},{"id":"riverflow-v2.6-pro","name":"Sourceful: Riverflow V2.6 Pro","created":1793289528,"description":"Riverflow 2.6 Pro is the flagship model of Sourceful's Riverflow 2.6 lineup, a unified text-to-image and image-to-image family that treats generation as a production workflow: an integrated reasoning model plans...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.255,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.02,"max_cost":1.02},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":320.3879835659811,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1281.5519342639243,"max_cost":1281.5519342639243},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.6-pro-20261029","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","5:4","4:5","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["png","jpeg","webp"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10},"size":{"type":"boolean"}},"unreported_cost_usd":0.13}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2.1-turbo","name":"Qwen: Qwen Image 2.1 Turbo","created":1792194104,"description":"Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0276,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.1104,"max_cost":0.1104},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":34.67728763302383,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":138.70915053209532,"max_cost":138.70915053209532},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-2.1-turbo-20261016","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.0184,"tiers":[{"resolution":null,"quality":null,"usd":0.0184}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.0184,"tiers":[{"resolution":null,"quality":null,"usd":0.0184}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":4},"seed":{"type":"boolean"}},"unreported_cost_usd":0.0184}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-2.1-pro","name":"Qwen: Qwen Image 2.1 Pro","created":1792194075,"description":"Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.069,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.276,"max_cost":0.276},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":86.6932190825596,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":346.7728763302384,"max_cost":346.7728763302384},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-2.1-pro-20261016","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.046,"tiers":[{"resolution":null,"quality":null,"usd":0.046}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.046,"tiers":[{"resolution":null,"quality":null,"usd":0.046}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":4},"seed":{"type":"boolean"}},"unreported_cost_usd":0.046}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-3-image-klein","name":"Black Forest Labs: FLUX 3 Image Klein","created":1792083863,"description":"FLUX 3 Image Klein is an open-weights image generation and editing model from Black Forest Labs. It is suited for text-to-image, multi-reference editing that keeps characters and subjects consistent across...","context_length":46864,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.05399999999999999,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.21599999999999997,"max_cost":0.21599999999999997},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":67.8468671080901,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":271.3874684323604,"max_cost":271.3874684323604},"per_request_limits":null,"top_provider":{"context_length":46864,"max_completion_tokens":42177,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"black-forest-labs/flux-3-image-klein-20261015","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.036,"tiers":[{"resolution":null,"quality":null,"usd":0.036}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"black-forest-labs":{"max_usd":0.036,"tiers":[{"resolution":null,"quality":null,"usd":0.036}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"black-forest-labs","parameters":{"resolution":{"type":"enum","values":["768","1K","1.5K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["21:9","2:1","16:9","3:2","7:5","4:3","5:4","1:1","4:5","3:4","5:7","2:3","9:16","1:2","9:21","auto"]},"output_format":{"type":"enum","values":["jpeg","png"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10},"seed":{"type":"boolean"}},"unreported_cost_usd":0.008}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-flash","name":"ByteDance Seed: Seedream 5.0 Flash","created":1790889880,"description":"Seedream 5.0 Flash is an image generation and editing model from ByteDance Seed. It is the fast, cost-efficient tier of the Seedream 5.0 family, suited for high-volume production and interactive...","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.026999999999999996,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.10799999999999998,"max_cost":0.10799999999999998},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":33.92343355404505,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":135.6937342161802,"max_cost":135.6937342161802},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-flash-20261001","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.018,"tiers":[{"resolution":null,"quality":null,"usd":0.018}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.018,"tiers":[{"resolution":null,"quality":null,"usd":0.018}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.018}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"flux-3-image","name":"Black Forest Labs: FLUX 3 Image","created":1790885807,"description":"FLUX.3 Image is Black Forest Labs' flagship image generation and editing model. It handles text-to-image and multi-reference editing with up to 10 input images, and renders at fixed resolution tiers...","context_length":46864,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.9105,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":3.642,"max_cost":3.642},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":1143.973564850297,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":4575.894259401188,"max_cost":4575.894259401188},"per_request_limits":null,"top_provider":{"context_length":46864,"max_completion_tokens":42177,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"black-forest-labs/flux-3-image-20261001","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.607,"tiers":[{"resolution":null,"quality":null,"usd":0.607}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"black-forest-labs":{"max_usd":0.607,"tiers":[{"resolution":null,"quality":null,"usd":0.607}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"black-forest-labs","parameters":{"resolution":{"type":"enum","values":["768","1K","1.5K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["21:9","2:1","16:9","3:2","7:5","4:3","5:4","1:1","4:5","3:4","5:7","2:3","9:16","1:2","9:21","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10}},"unreported_cost_usd":0.041}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-flash","name":"Recraft: Recraft V4.1 Flash","created":1790177946,"description":"Recraft V4.1 Flash is a text-to-image model from Recraft, the speed and cost tier of the V4.1 family. It generates ~1K raster images in about 1.5 seconds end to end,...","context_length":65536,"architecture":{"modality":"text->image","input_modalities":["text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0105,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.042,"max_cost":0.042},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":13.192446382128633,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":52.76978552851453,"max_cost":52.76978552851453},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-flash-20260923","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.007,"tiers":[{"resolution":null,"quality":null,"usd":0.007}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.007,"tiers":[{"resolution":null,"quality":null,"usd":0.007}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6}},"unreported_cost_usd":0.007}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-lite","name":"ByteDance Seed: Seedream 5.0 Lite","created":1786650094,"description":"Seedream 5.0 Lite is an image generation model from ByteDance Seed. It is suited for professional visual creation that benefits from web-connected retrieval, complex-prompt comprehension, visual references, and broad knowledge...","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.052500000000000005,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.21000000000000002,"max_cost":0.21000000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":65.96223191064317,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":263.8489276425727,"max_cost":263.8489276425727},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-lite-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":4},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-5-0-pro","name":"ByteDance Seed: Seedream 5.0 Pro","created":1786578139,"description":"Seedream 5.0 Pro is an image generation and editing model from ByteDance Seed. It is suited for commercial visual-production workflows that require precise editing control, lifelike scenes, and natural rendering.","context_length":0,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0045000000000000005,"image_output":0.135,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045000000000000005,"max_completion_cost":0.54,"max_cost":0.5445},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":5.653905592340843,"image_output":169.61716777022528,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.653905592340843,"max_completion_cost":678.4686710809011,"max_cost":684.1225766732418},"per_request_limits":null,"top_provider":{"context_length":0,"max_completion_tokens":0,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-5-0-pro-20260812","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.09,"tiers":[{"resolution":null,"quality":null,"usd":0.09}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.09,"tiers":[{"resolution":null,"quality":null,"usd":0.09}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.045}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"grok-imagine-image-2.0","name":"xAI: Grok Imagine Image 2.0","created":1786486044,"description":"Grok Imagine Image 2.0 is an image generation and editing model from xAI. It is suited for creating images from text prompts and editing images from references, with low and...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Grok","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.015,"image_output":0.12,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.015,"max_completion_cost":0.48,"max_cost":0.495},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":18.846351974469474,"image_output":150.7708157957558,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":18.846351974469474,"max_completion_cost":603.0832631830232,"max_cost":621.9296151574927},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"x-ai/grok-imagine-image-2.0-20260811","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.01,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"xai":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.01,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"xai","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","3:4","4:3","9:16","16:9","2:3","3:2","9:19.5","19.5:9","9:20","20:9","1:2","2:1","auto"]},"quality":{"type":"enum","values":["low","medium"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":3}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3","name":"Qwen: Qwen Image 3","created":1785894548,"description":"Qwen Image 3 is a unified image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with a richer world...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0045000000000000005,"image_output":0.045,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045000000000000005,"max_completion_cost":0.18,"max_cost":0.1845},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":5.653905592340843,"image_output":56.53905592340842,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.653905592340843,"max_completion_cost":226.15622369363368,"max_cost":231.81012928597454},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-3-20260805","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.03,"tiers":[{"resolution":null,"quality":null,"usd":0.03}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.03,"tiers":[{"resolution":null,"quality":null,"usd":0.03}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":3},"seed":{"type":"boolean"}},"unreported_cost_usd":0.03}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"qwen-image-3-pro","name":"Qwen: Qwen Image 3 Pro","created":1785894548,"description":"Qwen Image 3 Pro is an image generation and editing model from Qwen. It supports precise rendering of text and details as small as 10px, along with richer world knowledge...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Qwen","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0045000000000000005,"image_output":0.11249999999999999,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0045000000000000005,"max_completion_cost":0.44999999999999996,"max_cost":0.45449999999999996},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":5.653905592340843,"image_output":141.34763980852105,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":5.653905592340843,"max_completion_cost":565.3905592340842,"max_cost":571.044464826425},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"qwen/qwen-image-3-pro-20260805","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.075,"tiers":[{"resolution":null,"quality":null,"usd":0.075}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"alibaba":{"max_usd":0.075,"tiers":[{"resolution":null,"quality":null,"usd":0.075}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.003,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"alibaba","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","1:4","2:1","2:3","3:2","3:4","4:1","4:3","4:5","5:4","9:16","16:9"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":3},"seed":{"type":"boolean"}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-large","name":"Krea: Krea 2 Large","created":1784574931,"description":"Krea 2 Large is Krea's high-capability image generation model, more than twice the size of Krea 2 Medium. Its lighter post-training gives images a rawer, more textured, and flexible character,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.10500000000000001,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.42000000000000004,"max_cost":0.42000000000000004},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":131.92446382128634,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":527.6978552851454,"max_cost":527.6978552851454},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-large-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.07,"tiers":[{"resolution":null,"quality":null,"usd":0.07}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.07,"tiers":[{"resolution":null,"quality":null,"usd":0.07}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.06}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-medium","name":"Krea: Krea 2 Medium","created":1784574928,"description":"Krea 2 Medium is Krea's balanced, cost-efficient image generation model and a practical starting point for a broad range of use cases. Its extensive post-training supports stable, consistent generations, with...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.06,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.24,"max_cost":0.24},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":75.3854078978779,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":301.5416315915116,"max_cost":301.5416315915116},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-medium-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.03}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"krea-2-medium-turbo","name":"Krea: Krea 2 Medium Turbo","created":1784574923,"description":"Krea 2 Medium Turbo is a distilled, speed-focused variant of Krea 2 Medium from Krea. It is designed for rapid iteration and graphic design exploration where fast generation is the...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Media","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.03,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.12,"max_cost":0.12},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":37.69270394893895,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":150.7708157957558,"max_cost":150.7708157957558},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"krea/krea-2-medium-turbo-20260720","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.02,"tiers":[{"resolution":null,"quality":null,"usd":0.02}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"krea":{"max_usd":0.02,"tiers":[{"resolution":null,"quality":null,"usd":0.02}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"krea","parameters":{"resolution":{"type":"enum","values":["1K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:2","16:9","4:5","2:3","9:16"]},"input_references":{"type":"range","min":0,"max":1},"seed":{"type":"boolean"}},"unreported_cost_usd":0.015}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"riverflow-v2.5-pro","name":"Sourceful: Riverflow V2.5 Pro","created":1780584991,"description":"Riverflow V2.5 Pro is the most powerful variant of Sourceful's Riverflow 2.5 lineup, best for top-tier control and quality-sensitive outputs. The Riverflow 2.5 series is a unified text-to-image and image-to-image...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.255,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.02,"max_cost":1.02},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":320.3879835659811,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1281.5519342639243,"max_cost":1281.5519342639243},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.5-pro-20260605","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["xhigh","high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.17,"tiers":[{"resolution":null,"quality":null,"usd":0.17}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["png","jpeg","webp"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":10}},"unreported_cost_usd":0.13}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"riverflow-v2.5-fast","name":"Sourceful: Riverflow V2.5 Fast","created":1780584983,"description":"Riverflow V2.5 Fast is the speed-optimized variant of Sourceful's Riverflow 2.5 lineup, best for production deployments and latency-critical workflows. The Riverflow 2.5 series is a unified text-to-image and image-to-image family...","context_length":32768,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.0315,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.126,"max_cost":0.126},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":39.577339146385896,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":158.30935658554358,"max_cost":158.30935658554358},"per_request_limits":null,"top_provider":{"context_length":32768,"max_completion_tokens":29491,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"sourceful/riverflow-v2.5-fast-20260605","alias_ids":null,"forwarded_model_id":null,"reasoning":{"mandatory":true,"supported_efforts":["high","medium","low"],"default_effort":"medium"},"image_pricing":{"max_usd":0.021,"tiers":[{"resolution":null,"quality":null,"usd":0.021}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"sourceful":{"max_usd":0.021,"tiers":[{"resolution":null,"quality":null,"usd":0.021}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"sourceful","parameters":{"resolution":{"type":"enum","values":["1K","2K"]},"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","3:2","2:3","16:9","9:16","21:9","auto"]},"output_format":{"type":"enum","values":["jpeg"]},"background":{"type":"enum","values":["auto","transparent","opaque"]},"n":{"type":"range","min":1,"max":1},"input_references":{"type":"range","min":0,"max":4}},"unreported_cost_usd":0.019}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-pro-vector","name":"Recraft: Recraft V4.1 Pro Vector","created":1778707395,"description":"Recraft V4.1 Pro Vector is the vector (SVG) variant of Recraft V4.1 Pro, tuned for high aesthetics. It supports text and image inputs and produces higher-resolution SVG image output across...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.44999999999999996,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.7999999999999998,"max_cost":1.7999999999999998},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":565.3905592340842,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":2261.562236936337,"max_cost":2261.562236936337},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-pro-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.3}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-vector","name":"Recraft: Recraft V4.1 Vector","created":1778707392,"description":"Recraft V4.1 Vector is the vector (SVG) variant of Recraft V4.1, tuned for high aesthetics. It supports text and image inputs and produces SVG image output across multiple aspect ratios,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.12,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.48,"max_cost":0.48},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":150.7708157957558,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":603.0832631830232,"max_cost":603.0832631830232},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.08}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-utility-pro","name":"Recraft: Recraft V4.1 Utility Pro","created":1778707389,"description":"Recraft V4.1 Utility Pro is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios — double...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.315,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.26,"max_cost":1.26},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":395.77339146385896,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1583.0935658554358,"max_cost":1583.0935658554358},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-utility-pro-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.21}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-utility","name":"Recraft: Recraft V4.1 Utility","created":1778707387,"description":"Recraft V4.1 Utility is a general-purpose image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with typical generation...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.052500000000000005,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.21000000000000002,"max_cost":0.21000000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":65.96223191064317,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":263.8489276425727,"max_cost":263.8489276425727},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-utility-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1-pro","name":"Recraft: Recraft V4.1 Pro","created":1778707384,"description":"Recraft V4.1 Pro is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.315,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.26,"max_cost":1.26},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":395.77339146385896,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1583.0935658554358,"max_cost":1583.0935658554358},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-pro-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.21,"tiers":[{"resolution":null,"quality":null,"usd":0.21}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.21}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4.1","name":"Recraft: Recraft V4.1","created":1778707381,"description":"Recraft V4.1 is an image generation model from Recraft tuned for high aesthetics. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios, with...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.052500000000000005,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.21000000000000002,"max_cost":0.21000000000000002},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":65.96223191064317,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":263.8489276425727,"max_cost":263.8489276425727},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4.1-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.035,"tiers":[{"resolution":null,"quality":null,"usd":0.035}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.035}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-pro-vector","name":"Recraft: Recraft V4 Pro Vector","created":1778707334,"description":"Recraft V4 Pro Vector is the vector (SVG) variant of Recraft V4 Pro. It supports text and image inputs and produces vector image output across multiple aspect ratios at the...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.44999999999999996,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.7999999999999998,"max_cost":1.7999999999999998},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":565.3905592340842,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":2261.562236936337,"max_cost":2261.562236936337},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-pro-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.3,"tiers":[{"resolution":null,"quality":null,"usd":0.3}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.3}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-vector","name":"Recraft: Recraft V4 Vector","created":1778707333,"description":"Recraft V4 Vector is the vector (SVG) variant of Recraft V4. It supports text and image inputs and produces vector image output across multiple aspect ratios. Compared to the raster...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.12,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.48,"max_cost":0.48},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":150.7708157957558,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":603.0832631830232,"max_cost":603.0832631830232},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-vector-20260514","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.08,"tiers":[{"resolution":null,"quality":null,"usd":0.08}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"output_format":{"type":"enum","values":["svg"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.08}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4-pro","name":"Recraft: Recraft V4 Pro","created":1778185441,"description":"Recraft V4 Pro is an image generation model from Recraft. It supports text and image inputs with image output at ~2K resolution across multiple aspect ratios, double the resolution of...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.375,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1.5,"max_cost":1.5},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":471.15879936173684,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":1884.6351974469474,"max_cost":1884.6351974469474},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-pro-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.25,"tiers":[{"resolution":null,"quality":null,"usd":0.25}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.25,"tiers":[{"resolution":null,"quality":null,"usd":0.25}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.25}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v4","name":"Recraft: Recraft V4","created":1778185437,"description":"Recraft V4 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. It delivers stronger compositional judgment,...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.06,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.24,"max_cost":0.24},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":75.3854078978779,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":301.5416315915116,"max_cost":301.5416315915116},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v4-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"recraft-v3","name":"Recraft: Recraft V3","created":1778185433,"description":"Recraft V3 is an image generation model from Recraft. It supports text and image inputs with image output at ~1K resolution across multiple aspect ratios. Supports the following `image_config` parameters:...","context_length":65536,"architecture":{"modality":"text+image->image","input_modalities":["text","image"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.06,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.24,"max_cost":0.24},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":75.3854078978779,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":301.5416315915116,"max_cost":301.5416315915116},"per_request_limits":null,"top_provider":{"context_length":65536,"max_completion_tokens":58982,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"recraft/recraft-v3-20260413","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"recraft":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"recraft","parameters":{"aspect_ratio":{"type":"enum","values":["1:1","4:3","3:4","16:9","9:16","auto"]},"n":{"type":"range","min":1,"max":6},"input_references":{"type":"range","min":0,"max":1}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}},{"id":"seedream-4.5","name":"ByteDance Seed: Seedream 4.5","created":1766519506,"description":"Seedream 4.5 is the latest in-house image generation model developed by ByteDance. Compared with Seedream 4.0, it delivers comprehensive improvements, especially in editing consistency, including better preservation of subject details,...","context_length":4096,"architecture":{"modality":"text+image->image","input_modalities":["image","text"],"output_modalities":["image"],"tokenizer":"Other","instruct_type":null},"pricing":{"prompt":0.0,"completion":0.0,"request":0.0,"image":0.0,"image_output":0.06,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":0.24,"max_cost":0.24},"sats_pricing":{"prompt":0.0,"completion":0.0,"request":0.001,"image":0.0,"image_output":75.3854078978779,"web_search":0.0,"internal_reasoning":0.0,"input_cache_read":0.0,"input_cache_write":0.0,"max_prompt_cost":0.0,"max_completion_cost":301.5416315915116,"max_cost":301.5416315915116},"per_request_limits":null,"top_provider":{"context_length":4096,"max_completion_tokens":3686,"is_moderated":false},"enabled":true,"upstream_provider_id":"openrouter","canonical_slug":"bytedance-seed/seedream-4.5-20251203","alias_ids":null,"forwarded_model_id":null,"image_pricing":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{"seed":{"max_usd":0.04,"tiers":[{"resolution":null,"quality":null,"usd":0.04}],"default_resolution":null,"default_quality":null,"resolutions":[],"qualities":[],"upscale":{},"unit":"image","output_token_usd":0.0,"input_text_token_usd":0.0,"input_image_token_usd":0.0,"max_input_image_tokens":null,"megapixel_usd":0.0,"default_steps":null,"input_image_usd":0.0,"input_images_included":0,"trust_upstream_cost":true,"endpoints":{},"endpoint_tag":"seed","parameters":{"resolution":{"type":"enum","values":["1K","2K","4K"]},"aspect_ratio":{"type":"enum","values":["1:1","1:2","2:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","9:19.5","19.5:9","9:20","20:9","9:21","21:9","auto"]},"n":{"type":"range","min":1,"max":10},"input_references":{"type":"range","min":0,"max":14},"seed":{"type":"boolean"}},"unreported_cost_usd":0.04}},"endpoint_tag":null,"parameters":{},"unreported_cost_usd":null}}]}