{
"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-4.5": {
"id": "anthropic/claude-sonnet-4.5",
"name": "Anthropic: Claude Sonnet 4.5",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image",
"file"
],
"output": [
"text"
]
},
"context": 1000000,
"max_output_tokens": 64000,
"cost": {
"input": 3e-06,
"output": 1.5e-05
},
"vtcode": {
"variant": "OpenRouterAnthropicClaudeSonnet45",
"constant": "ANTHROPIC_CLAUDE_SONNET_4_5",
"vendor": "anthropic",
"display": "Claude Sonnet 4.5",
"description": "Anthropic Claude Sonnet 4.5 listing",
"efficient": false,
"top_tier": true,
"generation": "2025-10-15",
"doc_comment": "Claude Sonnet 4.5 - Anthropic Claude Sonnet 4.5 listing"
}
},
"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": "OpenRouterDeepseekChat",
"constant": "DEEPSEEK_CHAT",
"vendor": "deepseek",
"display": "DeepSeek V3.2 Chat",
"description": "DeepSeek official chat model via OpenRouter",
"efficient": true,
"top_tier": true,
"generation": "V3.2",
"doc_comment": "DeepSeek V3.2 Chat - Official chat model via OpenRouter"
}
},
"deepseek/deepseek-chat-v3.1": {
"id": "deepseek/deepseek-chat-v3.1",
"name": "DeepSeek: DeepSeek V3.1",
"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": "OpenRouterDeepSeekChatV31",
"constant": "DEEPSEEK_CHAT_V3_1",
"vendor": "deepseek",
"display": "DeepSeek Chat v3.1",
"description": "Advanced DeepSeek model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "2025-08-21",
"doc_comment": "DeepSeek Chat v3.1 - Advanced DeepSeek 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": "OpenRouterDeepseekReasoner",
"constant": "DEEPSEEK_REASONER",
"vendor": "deepseek",
"display": "DeepSeek V3.2 Reasoner",
"description": "DeepSeek thinking mode model via OpenRouter with deliberate reasoning output",
"efficient": false,
"top_tier": true,
"generation": "V3.2",
"doc_comment": "DeepSeek V3.2 Reasoner - Thinking mode via OpenRouter"
}
},
"deepseek/deepseek-v3.2": {
"id": "deepseek/deepseek-v3.2",
"name": "DeepSeek: DeepSeek V3.2",
"reasoning": true,
"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": "OpenRouterDeepSeekV32",
"constant": "DEEPSEEK_V3_2",
"vendor": "deepseek",
"display": "DeepSeek V3.2",
"description": "DeepSeek V3.2 model with thinking support via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "V3.2",
"doc_comment": "DeepSeek V3.2 - Standard model with thinking support via OpenRouter"
}
},
"deepseek/deepseek-v3.2-exp": {
"id": "deepseek/deepseek-v3.2-exp",
"name": "DeepSeek: DeepSeek V3.2 Exp",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 163840,
"max_output_tokens": null,
"cost": {
"input": 2.7e-07,
"output": 4e-07
},
"vtcode": {
"variant": "OpenRouterDeepSeekV32Exp",
"constant": "DEEPSEEK_V3_2_EXP",
"vendor": "deepseek",
"display": "DeepSeek V3.2 Exp",
"description": "Experimental DeepSeek V3.2 listing",
"efficient": false,
"top_tier": true,
"generation": "V3.2-Exp",
"doc_comment": "DeepSeek V3.2 Exp - Experimental DeepSeek V3.2 listing"
}
},
"deepseek/deepseek-v3.2-speciale": {
"id": "deepseek/deepseek-v3.2-speciale",
"name": "DeepSeek: DeepSeek V3.2 Speciale",
"reasoning": true,
"tool_call": false,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 8192,
"cost": {
"input": 5.5e-06,
"output": 2.2e-05
},
"vtcode": {
"variant": "OpenRouterDeepSeekV32Speciale",
"constant": "DEEPSEEK_V3_2_SPECIALE",
"vendor": "deepseek",
"display": "DeepSeek V3.2 Speciale",
"description": "DeepSeek V3.2 Speciale - Enhanced reasoning model (no tool-use)",
"efficient": false,
"top_tier": true,
"generation": "V3.2",
"doc_comment": "DeepSeek V3.2 Speciale - Enhanced reasoning with maxed-out capabilities"
}
},
"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-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"
}
},
"qwen/qwen3-14b": {
"id": "qwen/qwen3-14b",
"name": "Qwen: Qwen3 14B",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 40960,
"max_output_tokens": 40960,
"cost": {
"input": 5e-08,
"output": 2.2e-07
},
"vtcode": {
"variant": "OpenRouterQwen314b",
"constant": "QWEN3_14B",
"vendor": "qwen",
"display": "Qwen3 14B",
"description": "Lightweight Qwen3 14B model",
"efficient": true,
"top_tier": false,
"generation": "Qwen3-14B",
"doc_comment": "Qwen3 14B - Lightweight Qwen3 14B model"
}
},
"qwen/qwen3-30b-a3b": {
"id": "qwen/qwen3-30b-a3b",
"name": "Qwen: Qwen3 30B A3B",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 40960,
"max_output_tokens": 40960,
"cost": {
"input": 6e-08,
"output": 2.2e-07
},
"vtcode": {
"variant": "OpenRouterQwen330bA3b",
"constant": "QWEN3_30B_A3B",
"vendor": "qwen",
"display": "Qwen3 30B A3B",
"description": "Active-parameter 30B Qwen3 model",
"efficient": false,
"top_tier": false,
"generation": "Qwen3-30B",
"doc_comment": "Qwen3 30B A3B - Active-parameter 30B Qwen3 model"
}
},
"qwen/qwen3-30b-a3b-instruct-2507": {
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen: Qwen3 30B A3B Instruct 2507",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 8e-08,
"output": 3.3e-07
},
"vtcode": {
"variant": "OpenRouterQwen330bA3bInstruct2507",
"constant": "QWEN3_30B_A3B_INSTRUCT_2507",
"vendor": "qwen",
"display": "Qwen3 30B A3B Instruct 2507",
"description": "Instruction-tuned Qwen3 30B A3B",
"efficient": false,
"top_tier": false,
"generation": "Qwen3-30B",
"doc_comment": "Qwen3 30B A3B Instruct 2507 - Instruction-tuned Qwen3 30B A3B"
}
},
"qwen/qwen3-30b-a3b-thinking-2507": {
"id": "qwen/qwen3-30b-a3b-thinking-2507",
"name": "Qwen: Qwen3 30B A3B Thinking 2507",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 8e-08,
"output": 2.9e-07
},
"vtcode": {
"variant": "OpenRouterQwen330bA3bThinking2507",
"constant": "QWEN3_30B_A3B_THINKING_2507",
"vendor": "qwen",
"display": "Qwen3 30B A3B Thinking 2507",
"description": "Deliberative Qwen3 30B A3B release",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-30B",
"doc_comment": "Qwen3 30B A3B Thinking 2507 - Deliberative Qwen3 30B A3B release"
}
},
"qwen/qwen3-32b": {
"id": "qwen/qwen3-32b",
"name": "Qwen: Qwen3 32B",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 40960,
"max_output_tokens": 40960,
"cost": {
"input": 5e-08,
"output": 2e-07
},
"vtcode": {
"variant": "OpenRouterQwen332b",
"constant": "QWEN3_32B",
"vendor": "qwen",
"display": "Qwen3 32B",
"description": "Dense 32B Qwen3 deployment",
"efficient": false,
"top_tier": false,
"generation": "Qwen3-32B",
"doc_comment": "Qwen3 32B - Dense 32B Qwen3 deployment"
}
},
"qwen/qwen3-8b": {
"id": "qwen/qwen3-8b",
"name": "Qwen: Qwen3 8B",
"reasoning": true,
"tool_call": false,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 20000,
"cost": {
"input": 3.5e-08,
"output": 1.38e-07
},
"vtcode": {
"variant": "OpenRouterQwen38b",
"constant": "QWEN3_8B",
"vendor": "qwen",
"display": "Qwen3 8B",
"description": "Compact Qwen3 8B deployment",
"efficient": true,
"top_tier": false,
"generation": "Qwen3-8B",
"doc_comment": "Qwen3 8B - Compact Qwen3 8B deployment"
}
},
"qwen/qwen3-coder": {
"id": "qwen/qwen3-coder",
"name": "Qwen: Qwen3 Coder 480B A35B",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 2.2e-07,
"output": 9.5e-07
},
"vtcode": {
"variant": "OpenRouterQwen3Coder",
"constant": "QWEN3_CODER",
"vendor": "qwen",
"display": "Qwen3 Coder",
"description": "Qwen3-based coding model tuned for IDE workflows",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-Coder",
"doc_comment": "Qwen3 Coder - Qwen3-based coding model tuned for IDE workflows"
}
},
"qwen/qwen3-coder-30b-a3b-instruct": {
"id": "qwen/qwen3-coder-30b-a3b-instruct",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 6e-08,
"output": 2.5e-07
},
"vtcode": {
"variant": "OpenRouterQwen3Coder30bA3bInstruct",
"constant": "QWEN3_CODER_30B_A3B_INSTRUCT",
"vendor": "qwen",
"display": "Qwen3 Coder 30B A3B Instruct",
"description": "Large Mixture-of-Experts coding deployment",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-Coder",
"doc_comment": "Qwen3 Coder 30B A3B Instruct - Large Mixture-of-Experts coding deployment"
}
},
"qwen/qwen3-coder-next": {
"id": "qwen/qwen3-coder-next",
"name": "Qwen: Qwen3 Coder Next",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 2.2e-07,
"output": 9.5e-07
},
"vtcode": {
"variant": "OpenRouterQwen3CoderNext",
"constant": "QWEN3_CODER_NEXT",
"vendor": "qwen",
"display": "Qwen3 Coder Next",
"description": "Next-generation Qwen3 coding model with enhanced reasoning",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-Coder",
"doc_comment": "Qwen3 Coder Next - Next-generation Qwen3 coding model with enhanced reasoning"
}
},
"qwen/qwen3-coder-flash": {
"id": "qwen/qwen3-coder-flash",
"name": "Qwen: Qwen3 Coder Flash",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 65536,
"cost": {
"input": 3e-07,
"output": 1.5e-06
},
"vtcode": {
"variant": "OpenRouterQwen3CoderFlash",
"constant": "QWEN3_CODER_FLASH",
"vendor": "qwen",
"display": "Qwen3 Coder Flash",
"description": "Latency optimised Qwen3 coding model",
"efficient": true,
"top_tier": false,
"generation": "Qwen3-Coder",
"doc_comment": "Qwen3 Coder Flash - Latency optimised Qwen3 coding model"
}
},
"qwen/qwen3-coder-plus": {
"id": "qwen/qwen3-coder-plus",
"name": "Qwen: Qwen3 Coder Plus",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 128000,
"max_output_tokens": 65536,
"cost": {
"input": 1e-06,
"output": 5e-06
},
"vtcode": {
"variant": "OpenRouterQwen3CoderPlus",
"constant": "QWEN3_CODER_PLUS",
"vendor": "qwen",
"display": "Qwen3 Coder Plus",
"description": "Premium Qwen3 coding model with long context",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-Coder",
"doc_comment": "Qwen3 Coder Plus - Premium Qwen3 coding model with long context"
}
},
"qwen/qwen3-next-80b-a3b-instruct": {
"id": "qwen/qwen3-next-80b-a3b-instruct",
"name": "Qwen: Qwen3 Next 80B A3B Instruct",
"reasoning": false,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": 262144,
"cost": {
"input": 1e-07,
"output": 8e-07
},
"vtcode": {
"variant": "OpenRouterQwen3Next80bA3bInstruct",
"constant": "QWEN3_NEXT_80B_A3B_INSTRUCT",
"vendor": "qwen",
"display": "Qwen3 Next 80B A3B Instruct",
"description": "Next-generation Qwen3 instruction model",
"efficient": false,
"top_tier": false,
"generation": "Qwen3-Next",
"doc_comment": "Qwen3 Next 80B A3B Instruct - Next-generation Qwen3 instruction model"
}
},
"qwen/qwen3-next-80b-a3b-thinking": {
"id": "qwen/qwen3-next-80b-a3b-thinking",
"name": "Qwen: Qwen3 Next 80B A3B Thinking",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 262144,
"max_output_tokens": null,
"cost": {
"input": 1.4e-07,
"output": 1.2e-06
},
"vtcode": {
"variant": "OpenRouterQwen3Next80bA3bThinking",
"constant": "QWEN3_NEXT_80B_A3B_THINKING",
"vendor": "qwen",
"display": "Qwen3 Next 80B A3B Thinking",
"description": "Next-generation Qwen3 reasoning release",
"efficient": false,
"top_tier": true,
"generation": "Qwen3-Next",
"doc_comment": "Qwen3 Next 80B A3B Thinking - Next-generation Qwen3 reasoning release"
}
},
"qwen/qwen3.5-plus-02-15": {
"id": "qwen/qwen3.5-plus-02-15",
"name": "Qwen: Qwen3.5-397B-A17B",
"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 task evaluations, the 3.5 series consistently demonstrates performance on par with state-of-the-art leading models. Compared to the 3 series, these models show a leap forward in both pure-text and multimodal capabilities.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"context": 1000000,
"max_output_tokens": 256000,
"cost": {
"input": 5e-07,
"output": 2.5e-06
},
"vtcode": {
"variant": "OpenRouterQwen35Plus0215",
"constant": "QWEN3_5_PLUS_02_15",
"vendor": "qwen",
"display": "Qwen3.5-397B-A17B",
"description": "Qwen3.5 Plus with hybrid linear attention and sparse MoE architecture, 1M context",
"efficient": false,
"top_tier": true,
"generation": "Qwen3.5-Plus",
"doc_comment": "Qwen3.5-397B-A17B - Native vision-language model with linear attention and sparse MoE, 1M context window"
}
},
"z-ai/glm-5": {
"id": "z-ai/glm-5",
"name": "Z.AI: GLM-5",
"description": "Z.ai's flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.",
"reasoning": true,
"tool_call": true,
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"context": 202752,
"vtcode": {
"variant": "OpenRouterZaiGlm5",
"constant": "Z_AI_GLM_5",
"vendor": "zai",
"display": "GLM-5",
"description": "Z.ai flagship GLM-5 model via OpenRouter",
"efficient": false,
"top_tier": true,
"generation": "GLM-5",
"doc_comment": "GLM-5 - Z.AI GLM-5 flagship foundation model via OpenRouter"
}
}
},
"default_model": "qwen/qwen3-coder"
}