{
"id": "openrouter",
"env": [
"OPENROUTER_API_KEY"
],
"api": "https://openrouter.ai/api/v1",
"name": "OpenRouter",
"doc": "https://openrouter.ai/models",
"models": {
"meta/muse-glimmer-30b": {
"id": "meta/muse-glimmer-30b",
"name": "Meta: Muse Glimmer 30B",
"description": "Meta Muse Glimmer 30B reasoning model via OpenRouter.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 131072,
"cost": {
"input": 3.5e-07,
"output": 1.5e-06,
"cache_read": 4e-08
},
"vtcode": {
"variant": "OpenRouterMetaMuseGlimmer30b",
"constant": "META_MUSE_GLIMMER_30B",
"vendor": "meta",
"display": "Muse Glimmer 30B (OpenRouter)",
"description": "Meta Muse Glimmer 30B reasoning model via OpenRouter",
"efficient": true,
"top_tier": false,
"generation": "Muse-Glimmer-30B",
"doc_comment": "Muse Glimmer 30B - Meta Muse Glimmer 30B reasoning model via OpenRouter"
}
},
"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-3.8-flash": {
"id": "google/gemini-3.8-flash",
"name": "Google: Gemini 3.8 Flash",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"file"
],
"output": [
"text"
]
},
"context": 1048576,
"vtcode": {
"variant": "OpenRouterGoogleGemini38Flash",
"constant": "GOOGLE_GEMINI_3_8_FLASH",
"vendor": "google",
"display": "Gemini 3.8 Flash",
"description": "Most intelligent Flash for long-horizon SWE, agents, and enterprise workflows with 1M context via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "3.8",
"doc_comment": "Gemini 3.8 Flash - Most intelligent Flash for long-horizon SWE, agents, and enterprise workflows via OpenRouter"
}
},
"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"
}
},
"z-ai/glm-5.3-flash": {
"id": "z-ai/glm-5.3-flash",
"name": "Z.AI: GLM-5.3 Flash",
"description": "Z.AI efficient multimodal model with hybrid sparse+linear attention (320B total / 18B active, 3.01x less attention compute, 4.44x smaller KV cache), 1M context and native vision for efficient coding and long-horizon agent tasks.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1310720,
"max_output_tokens": 131072,
"cost": {
"input": 1.5e-07,
"output": 5e-07,
"cache_read": 3e-08
},
"vtcode": {
"variant": "OpenRouterZaiGlm53Flash",
"constant": "ZAI_GLM_5_3_FLASH",
"vendor": "z-ai",
"display": "GLM-5.3 Flash",
"description": "Z.AI GLM-5.3 Flash efficient multimodal model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "5.3",
"doc_comment": "GLM-5.3 Flash - Z.AI efficient multimodal model with hybrid sparse+linear attention via OpenRouter"
}
},
"z-ai/glm-5.3-flashx": {
"id": "z-ai/glm-5.3-flashx",
"name": "Z.AI: GLM-5.3 FlashX",
"description": "Z.AI high-speed Flash variant with faster inference (up to 200 tok/s), sharing the Flash multimodal stack (320B total / 18B active), 1M context and native vision for efficient coding and long-horizon agent tasks.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1048576,
"max_output_tokens": 131072,
"cost": {
"input": 3.7e-07,
"output": 1.25e-06,
"cache_read": 7.5e-08
},
"vtcode": {
"variant": "OpenRouterZaiGlm53Flashx",
"constant": "ZAI_GLM_5_3_FLASHX",
"vendor": "z-ai",
"display": "GLM-5.3 FlashX",
"description": "Z.AI GLM-5.3 FlashX high-speed efficient multimodal model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "5.3",
"doc_comment": "GLM-5.3 FlashX - Z.AI high-speed Flash variant with faster inference via OpenRouter"
}
},
"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-k3": {
"id": "moonshotai/kimi-k3",
"name": "MoonshotAI: Kimi K3",
"description": "Kimi K3 is Kimi's most capable model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, it offers native visual understanding and a 1M-token context window for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1048576,
"max_output_tokens": 131072,
"cost": {
"input": 3e-06,
"output": 1.5e-05,
"cache_read": 3e-07
},
"vtcode": {
"variant": "OpenRouterMoonshotaiKimiK3",
"constant": "MOONSHOTAI_KIMI_K3",
"vendor": "moonshotai",
"display": "Kimi K3",
"description": "Kimi K3 2.8T parameter flagship with 1M context, native vision, and deep reasoning via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "K3",
"doc_comment": "Kimi K3 - Moonshot AI's 2.8T parameter flagship model via OpenRouter"
}
},
"xiaomi/mimo-v2.6-pro": {
"id": "xiaomi/mimo-v2.6-pro",
"name": "Xiaomi: MiMo-V2.6-Pro",
"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 workloads. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"context": 1048576,
"max_output_tokens": 131072,
"cost": {
"input": 4.35e-07,
"output": 8.7e-07,
"cache_read": 3.6e-09
},
"vtcode": {
"variant": "OpenRouterXiaomiMimoV26Pro",
"constant": "XIAOMI_MIMO_V2_6_PRO",
"vendor": "xiaomi",
"display": "MiMo-V2.6-Pro",
"description": "Xiaomi MiMo-V2.6-Pro flagship agentic model for complex software engineering via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "MiMo-V2.6",
"doc_comment": "MiMo-V2.6-Pro - Xiaomi's flagship agentic model for complex software engineering via OpenRouter"
}
},
"xiaomi/mimo-v2.6-flash": {
"id": "xiaomi/mimo-v2.6-flash",
"name": "Xiaomi: MiMo-V2.6-Flash",
"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 greater computational efficiency. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers strong performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"context": 1048576,
"max_output_tokens": 131072,
"cost": {
"input": 1.4e-07,
"output": 2.8e-07,
"cache_read": 2.8e-09
},
"vtcode": {
"variant": "OpenRouterXiaomiMimoV26Flash",
"constant": "XIAOMI_MIMO_V2_6_FLASH",
"vendor": "xiaomi",
"display": "MiMo-V2.6-Flash",
"description": "Xiaomi MiMo-V2.6-Flash efficient high-volume agentic model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "MiMo-V2.6",
"doc_comment": "MiMo-V2.6-Flash - Xiaomi's efficient high-volume agentic model via OpenRouter"
}
},
"xiaomi/mimo-v2.6-pro-ultraspeed": {
"id": "xiaomi/mimo-v2.6-pro-ultraspeed",
"name": "Xiaomi: MiMo-V2.6-Pro-UltraSpeed",
"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 the output speed. The model features a 1M-token context window and native multimodal capabilities. Optimized for agentic workflows, it delivers top-tier performance across coding, visual, general, and research scenarios, excelling at complex, long-horizon tasks with robust generalization across a diverse range of agent harnesses.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"context": 1048576,
"max_output_tokens": 131072,
"cost": {
"input": 4.35e-06,
"output": 8.7e-06,
"cache_read": 3.6e-08
},
"vtcode": {
"variant": "OpenRouterXiaomiMimoV26ProUltraspeed",
"constant": "XIAOMI_MIMO_V2_6_PRO_ULTRASPEED",
"vendor": "xiaomi",
"display": "MiMo-V2.6-Pro-UltraSpeed",
"description": "Xiaomi MiMo-V2.6-Pro-UltraSpeed fastest flagship variant via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "MiMo-V2.6",
"doc_comment": "MiMo-V2.6-Pro-UltraSpeed - Xiaomi's fastest flagship variant via OpenRouter"
}
}
},
"default_model": "xiaomi/mimo-v2.6-pro"
}