{
"id": "openrouter",
"env": [
"OPENROUTER_API_KEY"
],
"api": "https://openrouter.ai/api/v1",
"name": "OpenRouter",
"doc": "https://openrouter.ai/models",
"models": {
"mistralai/mistral-large-2512": {
"id": "mistralai/mistral-large-2512",
"name": "Mistral: Mistral Large 3 2512",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 8192,
"cost": {
"input": 2e-06,
"output": 6e-06
},
"vtcode": {
"variant": "OpenRouterMistralaiMistralLarge2512",
"constant": "MISTRALAI_MISTRAL_LARGE_2512",
"vendor": "mistralai",
"display": "Mistral Large 3 2512",
"description": "Mistral Large 3 2512 model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "Mistral-Large-3",
"doc_comment": "Mistral Large 3 2512 - Mistral Large 3 2512 model via OpenRouter"
}
},
"google/gemini-3.1-pro-preview": {
"id": "google/gemini-3.1-pro-preview",
"name": "Google: Gemini 3.1 Pro Preview",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"file"
],
"output": [
"text"
]
},
"context": 1048576,
"vtcode": {
"variant": "OpenRouterGoogleGemini31ProPreview",
"constant": "GOOGLE_GEMINI_3_1_PRO_PREVIEW",
"vendor": "google",
"display": "Gemini 3.1 Pro Preview",
"description": "Google Gemini 3.1 Pro model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "3.1",
"doc_comment": "Gemini 3.1 Pro Preview - Google Gemini 3.1 Pro model via OpenRouter"
}
},
"nvidia/nemotron-3-super-120b-a12b:free": {
"id": "nvidia/nemotron-3-super-120b-a12b:free",
"name": "NVIDIA: Nemotron 3 Super (free)",
"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 Mixture-of-Experts architecture with multi-token prediction (MTP), it delivers over 50% higher token generation compared to leading open models.",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 1000000,
"cost": {
"input": 0,
"output": 0
},
"vtcode": {
"variant": "OpenRouterNvidiaNemotron3Super120bA12bFree",
"constant": "NVIDIA_NEMOTRON_3_SUPER_120B_A12B_FREE",
"vendor": "nvidia",
"display": "Nemotron 3 Super (free)",
"description": "NVIDIA Nemotron 3 Super (free) model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "Nemotron-3",
"doc_comment": "Nemotron 3 Super (free) - NVIDIA's 120B hybrid MoE model via OpenRouter"
}
},
"stepfun/step-3.5-flash:free": {
"id": "stepfun/step-3.5-flash:free",
"name": "Step 3.5 Flash (free)",
"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. It is a reasoning model that is incredibly speed efficient even at long contexts.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 256000,
"vtcode": {
"variant": "OpenRouterStepfunStep35FlashFree",
"constant": "STEPFUN_STEP_3_5_FLASH_FREE",
"vendor": "stepfun",
"display": "Step 3.5 Flash (free)",
"description": "Step 3.5 Flash (free) model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "Step-3.5",
"doc_comment": "Step 3.5 Flash (free) - StepFun's most capable open-source reasoning model via OpenRouter"
}
},
"anthropic/claude-haiku-4.5": {
"id": "anthropic/claude-haiku-4.5",
"name": "Anthropic: Claude Haiku 4.5",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 200000,
"vtcode": {
"variant": "OpenRouterAnthropicClaudeHaiku45",
"constant": "ANTHROPIC_CLAUDE_HAIKU_4_5",
"vendor": "anthropic",
"display": "Claude Haiku 4.5",
"description": "Anthropic Claude Haiku 4.5 listing",
"efficient": true,
"top_tier": false,
"generation": "2025-10-15",
"doc_comment": "Claude Haiku 4.5 - Anthropic Claude Haiku 4.5 listing"
}
},
"nex-agi/deepseek-v3.1-nex-n1": {
"id": "nex-agi/deepseek-v3.1-nex-n1",
"name": "Nex AGI: DeepSeek V3.1 Nex N1",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 163840,
"max_output_tokens": 163840,
"cost": {
"input": 2e-07,
"output": 8e-07
},
"vtcode": {
"variant": "OpenRouterNexAgiDeepseekV31NexN1",
"constant": "NEX_AGI_DEEPSEEK_V3_1_NEX_N1",
"vendor": "nex-agi",
"display": "DeepSeek V3.1 Nex N1",
"description": "Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "V3.1-Nex",
"doc_comment": "DeepSeek V3.1 Nex N1 - Nex AGI DeepSeek V3.1 Nex N1 model via OpenRouter"
}
},
"anthropic/claude-sonnet-4.6": {
"id": "anthropic/claude-sonnet-4.6",
"name": "Anthropic: Claude Sonnet 4.6",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"file"
],
"output": [
"text"
]
},
"context": 1000000,
"max_output_tokens": 128000,
"cost": {
"input": 3e-06,
"output": 1.5e-05
},
"vtcode": {
"variant": "OpenRouterAnthropicClaudeSonnet46",
"constant": "ANTHROPIC_CLAUDE_SONNET_4_6",
"vendor": "anthropic",
"display": "Claude Sonnet 4.6",
"description": "Anthropic Claude Sonnet 4.6 listing",
"efficient": false,
"top_tier": true,
"generation": "2026-02-20",
"doc_comment": "Claude Sonnet 4.6 - Anthropic Claude Sonnet 4.6 listing"
}
},
"deepseek/deepseek-chat": {
"id": "deepseek/deepseek-chat",
"name": "DeepSeek: DeepSeek V3.2 Chat",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 8192,
"cost": {
"input": 2.8e-07,
"output": 1.1e-06
},
"vtcode": {
"variant": "OpenRouterDeepSeekV4Flash",
"constant": "DEEPSEEK_V4_FLASH",
"vendor": "deepseek",
"display": "DeepSeek V4 Flash",
"description": "DeepSeek V4 Flash model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "4",
"doc_comment": "DeepSeek V4 Flash - Official Flash model via OpenRouter"
}
},
"deepseek/deepseek-r1": {
"id": "deepseek/deepseek-r1",
"name": "DeepSeek: R1",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 163840,
"max_output_tokens": 163840,
"cost": {
"input": 4e-07,
"output": 2e-06
},
"vtcode": {
"variant": "OpenRouterDeepSeekR1",
"constant": "DEEPSEEK_R1",
"vendor": "deepseek",
"display": "DeepSeek R1",
"description": "DeepSeek R1 reasoning model with chain-of-thought",
"efficient": false,
"top_tier": true,
"generation": "2025-01-20",
"doc_comment": "DeepSeek R1 - DeepSeek R1 reasoning model with chain-of-thought"
}
},
"deepseek/deepseek-reasoner": {
"id": "deepseek/deepseek-reasoner",
"name": "DeepSeek: DeepSeek V3.2 Reasoner (Thinking)",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 8192,
"cost": {
"input": 5.5e-06,
"output": 2.2e-05
},
"vtcode": {
"variant": "OpenRouterDeepSeekV4Pro",
"constant": "DEEPSEEK_V4_PRO",
"vendor": "deepseek",
"display": "DeepSeek V4 Pro",
"description": "DeepSeek V4 Pro thinking mode model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "4",
"doc_comment": "DeepSeek V4 Pro - Thinking mode via OpenRouter"
}
},
"openai/gpt-5": {
"id": "openai/gpt-5",
"name": "OpenAI: GPT-5",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"file"
],
"output": [
"text"
]
},
"context": 400000,
"max_output_tokens": 128000,
"cost": {
"input": 1.25e-06,
"output": 1e-05
},
"vtcode": {
"variant": "OpenRouterOpenAIGpt5",
"constant": "OPENAI_GPT_5",
"vendor": "openai",
"display": "OpenAI GPT-5",
"description": "OpenAI GPT-5 model accessed through OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "2025-09-20",
"doc_comment": "OpenAI GPT-5 - OpenAI GPT-5 model accessed through OpenRouter"
}
},
"openai/gpt-5.5": {
"id": "openai/gpt-5.5",
"name": "OpenAI: GPT-5.5",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1050000,
"vtcode": {
"variant": "OpenRouterOpenAIGpt55",
"constant": "OPENAI_GPT_5_5",
"vendor": "openai",
"display": "OpenAI GPT-5.5",
"description": "OpenAI GPT-5.5 model accessed through OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "2026-04-23",
"doc_comment": "OpenAI GPT-5.5 - OpenAI GPT-5.5 model accessed through OpenRouter"
}
},
"openai/gpt-5-chat": {
"id": "openai/gpt-5-chat",
"name": "OpenAI: GPT-5 Chat",
"reasoning": false,
"tool_call": false,
"modalities": {
"input": [
"file",
"image",
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 16384,
"cost": {
"input": 1.25e-06,
"output": 1e-05
},
"vtcode": {
"variant": "OpenRouterOpenAIGpt5Chat",
"constant": "OPENAI_GPT_5_CHAT",
"vendor": "openai",
"display": "OpenAI GPT-5 Chat",
"description": "Chat optimised GPT-5 endpoint without tool use",
"efficient": false,
"top_tier": false,
"generation": "2025-09-20",
"doc_comment": "OpenAI GPT-5 Chat - Chat optimised GPT-5 endpoint without tool use"
}
},
"openai/gpt-oss-120b": {
"id": "openai/gpt-oss-120b",
"name": "OpenAI: gpt-oss-120b",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 131072,
"max_output_tokens": 131072,
"cost": {
"input": 4e-08,
"output": 4e-07
},
"vtcode": {
"variant": "OpenRouterOpenAIGptOss120b",
"constant": "OPENAI_GPT_OSS_120B",
"vendor": "openai",
"display": "OpenAI gpt-oss-120b",
"description": "Open-weight 120B reasoning model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "OSS-120B",
"doc_comment": "OpenAI gpt-oss-120b - Open-weight 120B reasoning model via OpenRouter"
}
},
"openai/gpt-oss-20b": {
"id": "openai/gpt-oss-20b",
"name": "OpenAI: gpt-oss-20b",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 131072,
"max_output_tokens": null,
"cost": {
"input": 3e-08,
"output": 1.4e-07
},
"vtcode": {
"variant": "OpenRouterOpenAIGptOss20b",
"constant": "OPENAI_GPT_OSS_20B",
"vendor": "openai",
"display": "OpenAI gpt-oss-20b",
"description": "Open-weight 20B deployment via OpenRouter",
"efficient": false,
"top_tier": false,
"generation": "OSS-20B",
"doc_comment": "OpenAI gpt-oss-20b - Open-weight 20B deployment via OpenRouter"
}
},
"moonshotai/kimi-k2.6": {
"id": "moonshotai/kimi-k2.6",
"name": "MoonshotAI: Kimi K2.6",
"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. Handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 8192,
"cost": {
"input": 9.5e-07,
"output": 4e-06
},
"vtcode": {
"variant": "OpenRouterMoonshotaiKimiK26",
"constant": "MOONSHOTAI_KIMI_K2_6",
"vendor": "moonshotai",
"display": "Kimi K2.6",
"description": "Kimi K2.6 multimodal agentic model for long-horizon coding and design via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "K2.6",
"doc_comment": "Kimi K2.6 - Moonshot AI's next-generation multimodal model for long-horizon coding and design via OpenRouter"
}
},
"moonshotai/kimi-k2.7-code": {
"id": "moonshotai/kimi-k2.7-code",
"name": "MoonshotAI: Kimi K2.7 Code",
"description": "Kimi K2.7 Code is Moonshot AI's most capable coding model, with a breakthrough in long-horizon coding tasks across Rust, Go, Python and more. Supports 256K context, multi-step tool invocation, and strong reasoning capabilities.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 32768,
"cost": {
"input": 9.5e-07,
"output": 4e-06
},
"vtcode": {
"variant": "OpenRouterMoonshotaiKimiK27Code",
"constant": "MOONSHOTAI_KIMI_K2_7_CODE",
"vendor": "moonshotai",
"display": "Kimi K2.7 Code",
"description": "Kimi K2.7 Code most capable coding model with long-horizon coding breakthrough via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "K2.7",
"doc_comment": "Kimi K2.7 Code - Moonshot AI's most capable coding model with long-horizon coding breakthrough via OpenRouter"
}
},
"xiaomi/mimo-v2.5-pro": {
"id": "xiaomi/mimo-v2.5-pro",
"name": "Xiaomi: MiMo-V2.5-Pro",
"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.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 1000000,
"cost": {
"input": 4.35e-07,
"output": 8.7e-07
},
"vtcode": {
"variant": "OpenRouterXiaomiMimoV25Pro",
"constant": "XIAOMI_MIMO_V2_5_PRO",
"vendor": "xiaomi",
"display": "MiMo-V2.5-Pro",
"description": "Xiaomi MiMo-V2.5-Pro flagship agentic model for complex software engineering via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "MiMo-V2.5",
"doc_comment": "MiMo-V2.5-Pro - Xiaomi's flagship agentic model for complex software engineering via OpenRouter"
}
},
"xiaomi/mimo-v2.5": {
"id": "xiaomi/mimo-v2.5",
"name": "Xiaomi: MiMo-V2.5",
"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 tasks. Its 1M context window supports complete documents, extended conversations, and complex task contexts in a single pass.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1000000,
"max_output_tokens": 131072,
"cost": {
"input": 1.4e-07,
"output": 2.8e-07
},
"vtcode": {
"variant": "OpenRouterXiaomiMimoV25",
"constant": "XIAOMI_MIMO_V2_5",
"vendor": "xiaomi",
"display": "MiMo-V2.5",
"description": "Xiaomi MiMo-V2.5 omnimodal agentic model for complex software engineering via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "MiMo-V2.5",
"doc_comment": "MiMo-V2.5 - Xiaomi's omnimodal agentic model for complex software engineering via OpenRouter"
}
}
},
"default_model": "xiaomi/mimo-v2.5-pro"
}