Tool Config Files

# LiteLLM Proxy Configuration
# Generated on 2026-05-20
# Includes 16 active providers

model_list:
  - model_name: aihubmix/coding-glm-5.1-free
    litellm_params:
      model: aihubmix/coding-glm-5.1-free
      api_base: https://aihubmix.com/v1
      api_key: "YOUR_AIHUBMIX_API_KEY"
  - model_name: aihubmix/coding-minimax-m2.7-free
    litellm_params:
      model: aihubmix/coding-minimax-m2.7-free
      api_base: https://aihubmix.com/v1
      api_key: "YOUR_AIHUBMIX_API_KEY"
  - model_name: openrouter/glm-4.5-air:free
    litellm_params:
      model: openrouter/z-ai/glm-4.5-air:free
      api_base: https://openrouter.ai/api/v1
      api_key: "YOUR_OPENROUTER_API_KEY"
  - model_name: openrouter/minimax-m2.5:free
    litellm_params:
      model: openrouter/minimax/minimax-m2.5:free
      api_base: https://openrouter.ai/api/v1
      api_key: "YOUR_OPENROUTER_API_KEY"
  - model_name: nvidia-nim/llama-3.3-70b-instruct
    litellm_params:
      model: nvidia_nim/meta/llama-3.3-70b-instruct
      api_base: https://integrate.api.nvidia.com/v1
      api_key: "YOUR_NVIDIA_NIM_API_KEY"
  - model_name: nvidia-nim/deepseek-v4-pro
    litellm_params:
      model: nvidia_nim/deepseek-ai/deepseek-v4-pro
      api_base: https://integrate.api.nvidia.com/v1
      api_key: "YOUR_NVIDIA_NIM_API_KEY"
  - model_name: groq/llama-3.3-70b-versatile
    litellm_params:
      model: groq/llama-3.3-70b-versatile
      api_base: https://api.groq.com/openai/v1
      api_key: "YOUR_GROQ_API_KEY"
  - model_name: groq/llama-4-scout-17b-16e-instruct
    litellm_params:
      model: groq/meta-llama/llama-4-scout-17b-16e-instruct
      api_base: https://api.groq.com/openai/v1
      api_key: "YOUR_GROQ_API_KEY"
  - model_name: cerebras/llama3.1-8b
    litellm_params:
      model: cerebras/llama3.1-8b
      api_base: https://api.cerebras.ai/v1
      api_key: "YOUR_CEREBRAS_API_KEY"
  - model_name: cerebras/qwen-3-235b-a22b-instruct-2507
    litellm_params:
      model: cerebras/qwen-3-235b-a22b-instruct-2507
      api_base: https://api.cerebras.ai/v1
      api_key: "YOUR_CEREBRAS_API_KEY"
  - model_name: cohere/command-a-03-2025
    litellm_params:
      model: cohere/command-a-03-2025
      api_base: https://api.cohere.ai/compatibility/v1
      api_key: "YOUR_COHERE_API_KEY"
  - model_name: cohere/command-r-plus
    litellm_params:
      model: cohere/command-r-plus
      api_base: https://api.cohere.ai/compatibility/v1
      api_key: "YOUR_COHERE_API_KEY"
  - model_name: huggingface/Llama-3.3-70B-Instruct
    litellm_params:
      model: huggingface/meta-llama/Llama-3.3-70B-Instruct
      api_base: https://router.huggingface.co/v1
      api_key: "YOUR_HUGGINGFACE_API_KEY"
  - model_name: huggingface/DeepSeek-V3-0324
    litellm_params:
      model: huggingface/deepseek-ai/DeepSeek-V3-0324
      api_base: https://router.huggingface.co/v1
      api_key: "YOUR_HUGGINGFACE_API_KEY"
  - model_name: sambanova/Meta-Llama-3.3-70B-Instruct
    litellm_params:
      model: sambanova/Meta-Llama-3.3-70B-Instruct
      api_base: https://api.sambanova.ai/v1
      api_key: "YOUR_SAMBANOVA_API_KEY"
  - model_name: sambanova/MiniMax-M2.5
    litellm_params:
      model: sambanova/MiniMax-M2.5
      api_base: https://api.sambanova.ai/v1
      api_key: "YOUR_SAMBANOVA_API_KEY"
  - model_name: github-models/gpt-4.1-mini
    litellm_params:
      model: github_models/openai/gpt-4.1-mini
      api_base: https://models.github.ai/inference
      api_key: "YOUR_GITHUB_MODELS_API_KEY"
  - model_name: github-models/llama-4-scout-17b-16e-instruct
    litellm_params:
      model: github_models/meta/llama-4-scout-17b-16e-instruct
      api_base: https://models.github.ai/inference
      api_key: "YOUR_GITHUB_MODELS_API_KEY"
  - model_name: modelscope/Qwen3-30B-A3B-Instruct-2507
    litellm_params:
      model: modelscope/Qwen/Qwen3-30B-A3B-Instruct-2507
      api_base: https://api-inference.modelscope.cn/v1
      api_key: "YOUR_MODELSCOPE_API_KEY"
  - model_name: modelscope/DeepSeek-V3.1
    litellm_params:
      model: modelscope/deepseek-ai/DeepSeek-V3.1
      api_base: https://api-inference.modelscope.cn/v1
      api_key: "YOUR_MODELSCOPE_API_KEY"
  - model_name: siliconflow/Qwen3-8B
    litellm_params:
      model: siliconflow/Qwen/Qwen3-8B
      api_base: https://api.siliconflow.com/v1
      api_key: "YOUR_SILICONFLOW_API_KEY"
  - model_name: siliconflow/DeepSeek-R1-Distill-Qwen-7B
    litellm_params:
      model: siliconflow/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
      api_base: https://api.siliconflow.com/v1
      api_key: "YOUR_SILICONFLOW_API_KEY"
  - model_name: bigmodel/glm-4.7-flash
    litellm_params:
      model: bigmodel/glm-4.7-flash
      api_base: https://open.bigmodel.cn/api/paas/v4
      api_key: "YOUR_BIGMODEL_API_KEY"
  - model_name: bigmodel/glm-4-flash-250414
    litellm_params:
      model: bigmodel/glm-4-flash-250414
      api_base: https://open.bigmodel.cn/api/paas/v4
      api_key: "YOUR_BIGMODEL_API_KEY"
  - model_name: cloudflare-workers-ai/gpt-oss-120b
    litellm_params:
      model: cloudflare_workers-ai/@cf/openai/gpt-oss-120b
      api_base: https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
      api_key: "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY"
  - model_name: cloudflare-workers-ai/llama-3.3-70b-instruct-fp8-fast
    litellm_params:
      model: cloudflare_workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast
      api_base: https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1
      api_key: "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY"
  - model_name: ollama-cloud/gpt-oss:120b
    litellm_params:
      model: ollama_cloud/gpt-oss:120b
      api_base: https://ollama.com/v1
      api_key: "YOUR_OLLAMA_CLOUD_API_KEY"
  - model_name: ollama-cloud/deepseek-v3.2
    litellm_params:
      model: ollama_cloud/deepseek-v3.2
      api_base: https://ollama.com/v1
      api_key: "YOUR_OLLAMA_CLOUD_API_KEY"
  - model_name: google-ai-studio/gemini-2.5-flash
    litellm_params:
      model: google_ai-studio/gemini-2.5-flash
      api_base: https://generativelanguage.googleapis.com/v1beta/openai
      api_key: "YOUR_GOOGLE_AI_STUDIO_API_KEY"
  - model_name: google-ai-studio/gemini-3-flash-preview
    litellm_params:
      model: google_ai-studio/gemini-3-flash-preview
      api_base: https://generativelanguage.googleapis.com/v1beta/openai
      api_key: "YOUR_GOOGLE_AI_STUDIO_API_KEY"
  - model_name: mistral/mistral-small-latest
    litellm_params:
      model: mistral/mistral-small-latest
      api_base: https://api.mistral.ai/v1
      api_key: "YOUR_MISTRAL_API_KEY"
  - model_name: mistral/open-mistral-nemo
    litellm_params:
      model: mistral/open-mistral-nemo
      api_base: https://api.mistral.ai/v1
      api_key: "YOUR_MISTRAL_API_KEY"

litellm_settings:
  drop_params: true
  set_verbose: false

Open WebUI Docs

Self-hosted ChatGPT-style web UI

Quick Start

1

Get API Keys

Obtain an API key from each provider's console
2

Replace placeholders

Replace all YOUR_*_API_KEY values with your real keys
3

Import config

Go to Open WebUI → Settings → Connections → Import
4

Save and reload

Click Save then refresh the page to apply

API Keys

Hugging Face Inference

Cloudflare Workers AI

Ollama Cloud

Google AI Studio

Mistral AI

Filename openwebui-connections.json

Format json

json

{
  "connections": [
    {
      "id": "aihubmix",
      "name": "AIHubMix",
      "api_base_url": "https://aihubmix.com/v1",
      "api_key": "YOUR_AIHUBMIX_API_KEY",
      "models": [
        {
          "id": "coding-glm-5.1-free",
          "name": "coding-glm-5.1-free"
        },
        {
          "id": "coding-minimax-m2.7-free",
          "name": "coding-minimax-m2.7-free"
        }
      ]
    },
    {
      "id": "openrouter",
      "name": "OpenRouter",
      "api_base_url": "https://openrouter.ai/api/v1",
      "api_key": "YOUR_OPENROUTER_API_KEY",
      "models": [
        {
          "id": "z-ai/glm-4.5-air:free",
          "name": "glm-4.5-air:free"
        },
        {
          "id": "minimax/minimax-m2.5:free",
          "name": "minimax-m2.5:free"
        },
        {
          "id": "nvidia/nemotron-3-super-120b-a12b:free",
          "name": "nemotron-3-super-120b-a12b:free"
        }
      ]
    },
    {
      "id": "nvidia-nim",
      "name": "NVIDIA NIM",
      "api_base_url": "https://integrate.api.nvidia.com/v1",
      "api_key": "YOUR_NVIDIA_NIM_API_KEY",
      "models": [
        {
          "id": "meta/llama-3.3-70b-instruct",
          "name": "llama-3.3-70b-instruct"
        },
        {
          "id": "deepseek-ai/deepseek-v4-pro",
          "name": "deepseek-v4-pro"
        },
        {
          "id": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
          "name": "llama-3.1-nemotron-ultra-253b-v1"
        }
      ]
    },
    {
      "id": "groq",
      "name": "Groq",
      "api_base_url": "https://api.groq.com/openai/v1",
      "api_key": "YOUR_GROQ_API_KEY",
      "models": [
        {
          "id": "llama-3.3-70b-versatile",
          "name": "llama-3.3-70b-versatile"
        },
        {
          "id": "meta-llama/llama-4-scout-17b-16e-instruct",
          "name": "llama-4-scout-17b-16e-instruct"
        },
        {
          "id": "moonshotai/kimi-k2-instruct",
          "name": "kimi-k2-instruct"
        }
      ]
    },
    {
      "id": "cerebras",
      "name": "Cerebras",
      "api_base_url": "https://api.cerebras.ai/v1",
      "api_key": "YOUR_CEREBRAS_API_KEY",
      "models": [
        {
          "id": "llama3.1-8b",
          "name": "llama3.1-8b"
        },
        {
          "id": "qwen-3-235b-a22b-instruct-2507",
          "name": "qwen-3-235b-a22b-instruct-2507"
        },
        {
          "id": "gpt-oss-120b",
          "name": "gpt-oss-120b"
        }
      ]
    },
    {
      "id": "cohere",
      "name": "Cohere",
      "api_base_url": "https://api.cohere.ai/compatibility/v1",
      "api_key": "YOUR_COHERE_API_KEY",
      "models": [
        {
          "id": "command-a-03-2025",
          "name": "command-a-03-2025"
        },
        {
          "id": "command-r-plus",
          "name": "command-r-plus"
        },
        {
          "id": "command-r7b-12-2024",
          "name": "command-r7b-12-2024"
        }
      ]
    },
    {
      "id": "huggingface",
      "name": "Hugging Face Inference",
      "api_base_url": "https://router.huggingface.co/v1",
      "api_key": "YOUR_HUGGINGFACE_API_KEY",
      "models": [
        {
          "id": "meta-llama/Llama-3.3-70B-Instruct",
          "name": "Llama-3.3-70B-Instruct"
        },
        {
          "id": "deepseek-ai/DeepSeek-V3-0324",
          "name": "DeepSeek-V3-0324"
        },
        {
          "id": "openai/gpt-oss-120b",
          "name": "gpt-oss-120b"
        }
      ]
    },
    {
      "id": "sambanova",
      "name": "SambaNova Cloud",
      "api_base_url": "https://api.sambanova.ai/v1",
      "api_key": "YOUR_SAMBANOVA_API_KEY",
      "models": [
        {
          "id": "Meta-Llama-3.3-70B-Instruct",
          "name": "Meta-Llama-3.3-70B-Instruct"
        },
        {
          "id": "MiniMax-M2.5",
          "name": "MiniMax-M2.5"
        },
        {
          "id": "Llama-4-Maverick-17B-128E-Instruct",
          "name": "Llama-4-Maverick-17B-128E-Instruct"
        }
      ]
    },
    {
      "id": "github-models",
      "name": "GitHub Models",
      "api_base_url": "https://models.github.ai/inference",
      "api_key": "YOUR_GITHUB_MODELS_API_KEY",
      "models": [
        {
          "id": "openai/gpt-4.1-mini",
          "name": "gpt-4.1-mini"
        },
        {
          "id": "meta/llama-4-scout-17b-16e-instruct",
          "name": "llama-4-scout-17b-16e-instruct"
        },
        {
          "id": "openai/o4-mini",
          "name": "o4-mini"
        }
      ]
    },
    {
      "id": "modelscope",
      "name": "ModelScope",
      "api_base_url": "https://api-inference.modelscope.cn/v1",
      "api_key": "YOUR_MODELSCOPE_API_KEY",
      "models": [
        {
          "id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
          "name": "Qwen3-30B-A3B-Instruct-2507"
        },
        {
          "id": "deepseek-ai/DeepSeek-V3.1",
          "name": "DeepSeek-V3.1"
        },
        {
          "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "name": "Qwen3-Coder-480B-A35B-Instruct"
        }
      ]
    },
    {
      "id": "siliconflow",
      "name": "SiliconFlow",
      "api_base_url": "https://api.siliconflow.com/v1",
      "api_key": "YOUR_SILICONFLOW_API_KEY",
      "models": [
        {
          "id": "Qwen/Qwen3-8B",
          "name": "Qwen3-8B"
        },
        {
          "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
          "name": "DeepSeek-R1-Distill-Qwen-7B"
        },
        {
          "id": "THUDM/GLM-Z1-9B-0414",
          "name": "GLM-Z1-9B-0414"
        }
      ]
    },
    {
      "id": "bigmodel",
      "name": "BigModel",
      "api_base_url": "https://open.bigmodel.cn/api/paas/v4",
      "api_key": "YOUR_BIGMODEL_API_KEY",
      "models": [
        {
          "id": "glm-4.7-flash",
          "name": "glm-4.7-flash"
        },
        {
          "id": "glm-4-flash-250414",
          "name": "glm-4-flash-250414"
        },
        {
          "id": "glm-4.1v-thinking-flash",
          "name": "glm-4.1v-thinking-flash"
        }
      ]
    },
    {
      "id": "cloudflare-workers-ai",
      "name": "Cloudflare Workers AI",
      "api_base_url": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
      "api_key": "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY",
      "models": [
        {
          "id": "@cf/openai/gpt-oss-120b",
          "name": "gpt-oss-120b"
        },
        {
          "id": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
          "name": "llama-3.3-70b-instruct-fp8-fast"
        },
        {
          "id": "@cf/meta/llama-4-scout-17b-16e-instruct",
          "name": "llama-4-scout-17b-16e-instruct"
        }
      ]
    },
    {
      "id": "ollama-cloud",
      "name": "Ollama Cloud",
      "api_base_url": "https://ollama.com/v1",
      "api_key": "YOUR_OLLAMA_CLOUD_API_KEY",
      "models": [
        {
          "id": "gpt-oss:120b",
          "name": "gpt-oss:120b"
        },
        {
          "id": "deepseek-v3.2",
          "name": "deepseek-v3.2"
        },
        {
          "id": "kimi-k2.5",
          "name": "kimi-k2.5"
        }
      ]
    },
    {
      "id": "google-ai-studio",
      "name": "Google AI Studio",
      "api_base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
      "api_key": "YOUR_GOOGLE_AI_STUDIO_API_KEY",
      "models": [
        {
          "id": "gemini-2.5-flash",
          "name": "gemini-2.5-flash"
        },
        {
          "id": "gemini-3-flash-preview",
          "name": "gemini-3-flash-preview"
        },
        {
          "id": "gemini-2.5-pro",
          "name": "gemini-2.5-pro"
        }
      ]
    },
    {
      "id": "mistral",
      "name": "Mistral AI",
      "api_base_url": "https://api.mistral.ai/v1",
      "api_key": "YOUR_MISTRAL_API_KEY",
      "models": [
        {
          "id": "mistral-small-latest",
          "name": "mistral-small-latest"
        },
        {
          "id": "open-mistral-nemo",
          "name": "open-mistral-nemo"
        },
        {
          "id": "codestral-latest",
          "name": "codestral-latest"
        },
        {
          "id": "magistral-small-latest",
          "name": "magistral-small-latest"
        }
      ]
    }
  ]
}

LobeChat Docs

Modern AI assistant UI with plugin support

Quick Start

1

Get API Keys

Obtain an API key from each provider's console
2

Replace placeholders

Replace all YOUR_*_API_KEY values with your real keys
3

Place config file

Save to ~/.lobe/providers.json
4

Restart app

Restart LobeChat and enable the provider in settings

API Keys

Hugging Face Inference

Cloudflare Workers AI

Ollama Cloud

Google AI Studio

Mistral AI

Filename lobechat-providers.json

Format json

json

{
  "providers": [
    {
      "id": "aihubmix",
      "name": "AIHubMix",
      "enabled": true,
      "apiKey": "YOUR_AIHUBMIX_API_KEY",
      "endpoint": "https://aihubmix.com/v1",
      "models": [
        {
          "id": "coding-glm-5.1-free",
          "displayName": "coding-glm-5.1-free",
          "enabled": true
        },
        {
          "id": "coding-minimax-m2.7-free",
          "displayName": "coding-minimax-m2.7-free",
          "enabled": true
        }
      ]
    },
    {
      "id": "openrouter",
      "name": "OpenRouter",
      "enabled": true,
      "apiKey": "YOUR_OPENROUTER_API_KEY",
      "endpoint": "https://openrouter.ai/api/v1",
      "models": [
        {
          "id": "z-ai/glm-4.5-air:free",
          "displayName": "glm-4.5-air:free",
          "enabled": true
        },
        {
          "id": "minimax/minimax-m2.5:free",
          "displayName": "minimax-m2.5:free",
          "enabled": true
        },
        {
          "id": "nvidia/nemotron-3-super-120b-a12b:free",
          "displayName": "nemotron-3-super-120b-a12b:free",
          "enabled": true
        }
      ]
    },
    {
      "id": "nvidia-nim",
      "name": "NVIDIA NIM",
      "enabled": true,
      "apiKey": "YOUR_NVIDIA_NIM_API_KEY",
      "endpoint": "https://integrate.api.nvidia.com/v1",
      "models": [
        {
          "id": "meta/llama-3.3-70b-instruct",
          "displayName": "llama-3.3-70b-instruct",
          "enabled": true
        },
        {
          "id": "deepseek-ai/deepseek-v4-pro",
          "displayName": "deepseek-v4-pro",
          "enabled": true
        },
        {
          "id": "nvidia/llama-3.1-nemotron-ultra-253b-v1",
          "displayName": "llama-3.1-nemotron-ultra-253b-v1",
          "enabled": true
        }
      ]
    },
    {
      "id": "groq",
      "name": "Groq",
      "enabled": true,
      "apiKey": "YOUR_GROQ_API_KEY",
      "endpoint": "https://api.groq.com/openai/v1",
      "models": [
        {
          "id": "llama-3.3-70b-versatile",
          "displayName": "llama-3.3-70b-versatile",
          "enabled": true
        },
        {
          "id": "meta-llama/llama-4-scout-17b-16e-instruct",
          "displayName": "llama-4-scout-17b-16e-instruct",
          "enabled": true
        },
        {
          "id": "moonshotai/kimi-k2-instruct",
          "displayName": "kimi-k2-instruct",
          "enabled": true
        }
      ]
    },
    {
      "id": "cerebras",
      "name": "Cerebras",
      "enabled": true,
      "apiKey": "YOUR_CEREBRAS_API_KEY",
      "endpoint": "https://api.cerebras.ai/v1",
      "models": [
        {
          "id": "llama3.1-8b",
          "displayName": "llama3.1-8b",
          "enabled": true
        },
        {
          "id": "qwen-3-235b-a22b-instruct-2507",
          "displayName": "qwen-3-235b-a22b-instruct-2507",
          "enabled": true
        },
        {
          "id": "gpt-oss-120b",
          "displayName": "gpt-oss-120b",
          "enabled": true
        }
      ]
    },
    {
      "id": "cohere",
      "name": "Cohere",
      "enabled": true,
      "apiKey": "YOUR_COHERE_API_KEY",
      "endpoint": "https://api.cohere.ai/compatibility/v1",
      "models": [
        {
          "id": "command-a-03-2025",
          "displayName": "command-a-03-2025",
          "enabled": true
        },
        {
          "id": "command-r-plus",
          "displayName": "command-r-plus",
          "enabled": true
        },
        {
          "id": "command-r7b-12-2024",
          "displayName": "command-r7b-12-2024",
          "enabled": true
        }
      ]
    },
    {
      "id": "huggingface",
      "name": "Hugging Face Inference",
      "enabled": true,
      "apiKey": "YOUR_HUGGINGFACE_API_KEY",
      "endpoint": "https://router.huggingface.co/v1",
      "models": [
        {
          "id": "meta-llama/Llama-3.3-70B-Instruct",
          "displayName": "Llama-3.3-70B-Instruct",
          "enabled": true
        },
        {
          "id": "deepseek-ai/DeepSeek-V3-0324",
          "displayName": "DeepSeek-V3-0324",
          "enabled": true
        },
        {
          "id": "openai/gpt-oss-120b",
          "displayName": "gpt-oss-120b",
          "enabled": true
        }
      ]
    },
    {
      "id": "sambanova",
      "name": "SambaNova Cloud",
      "enabled": true,
      "apiKey": "YOUR_SAMBANOVA_API_KEY",
      "endpoint": "https://api.sambanova.ai/v1",
      "models": [
        {
          "id": "Meta-Llama-3.3-70B-Instruct",
          "displayName": "Meta-Llama-3.3-70B-Instruct",
          "enabled": true
        },
        {
          "id": "MiniMax-M2.5",
          "displayName": "MiniMax-M2.5",
          "enabled": true
        },
        {
          "id": "Llama-4-Maverick-17B-128E-Instruct",
          "displayName": "Llama-4-Maverick-17B-128E-Instruct",
          "enabled": true
        }
      ]
    },
    {
      "id": "github-models",
      "name": "GitHub Models",
      "enabled": true,
      "apiKey": "YOUR_GITHUB_MODELS_API_KEY",
      "endpoint": "https://models.github.ai/inference",
      "models": [
        {
          "id": "openai/gpt-4.1-mini",
          "displayName": "gpt-4.1-mini",
          "enabled": true
        },
        {
          "id": "meta/llama-4-scout-17b-16e-instruct",
          "displayName": "llama-4-scout-17b-16e-instruct",
          "enabled": true
        },
        {
          "id": "openai/o4-mini",
          "displayName": "o4-mini",
          "enabled": true
        }
      ]
    },
    {
      "id": "modelscope",
      "name": "ModelScope",
      "enabled": true,
      "apiKey": "YOUR_MODELSCOPE_API_KEY",
      "endpoint": "https://api-inference.modelscope.cn/v1",
      "models": [
        {
          "id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
          "displayName": "Qwen3-30B-A3B-Instruct-2507",
          "enabled": true
        },
        {
          "id": "deepseek-ai/DeepSeek-V3.1",
          "displayName": "DeepSeek-V3.1",
          "enabled": true
        },
        {
          "id": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
          "displayName": "Qwen3-Coder-480B-A35B-Instruct",
          "enabled": true
        }
      ]
    },
    {
      "id": "siliconflow",
      "name": "SiliconFlow",
      "enabled": true,
      "apiKey": "YOUR_SILICONFLOW_API_KEY",
      "endpoint": "https://api.siliconflow.com/v1",
      "models": [
        {
          "id": "Qwen/Qwen3-8B",
          "displayName": "Qwen3-8B",
          "enabled": true
        },
        {
          "id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
          "displayName": "DeepSeek-R1-Distill-Qwen-7B",
          "enabled": true
        },
        {
          "id": "THUDM/GLM-Z1-9B-0414",
          "displayName": "GLM-Z1-9B-0414",
          "enabled": true
        }
      ]
    },
    {
      "id": "bigmodel",
      "name": "BigModel",
      "enabled": true,
      "apiKey": "YOUR_BIGMODEL_API_KEY",
      "endpoint": "https://open.bigmodel.cn/api/paas/v4",
      "models": [
        {
          "id": "glm-4.7-flash",
          "displayName": "glm-4.7-flash",
          "enabled": true
        },
        {
          "id": "glm-4-flash-250414",
          "displayName": "glm-4-flash-250414",
          "enabled": true
        },
        {
          "id": "glm-4.1v-thinking-flash",
          "displayName": "glm-4.1v-thinking-flash",
          "enabled": true
        }
      ]
    },
    {
      "id": "cloudflare-workers-ai",
      "name": "Cloudflare Workers AI",
      "enabled": true,
      "apiKey": "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY",
      "endpoint": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
      "models": [
        {
          "id": "@cf/openai/gpt-oss-120b",
          "displayName": "gpt-oss-120b",
          "enabled": true
        },
        {
          "id": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
          "displayName": "llama-3.3-70b-instruct-fp8-fast",
          "enabled": true
        },
        {
          "id": "@cf/meta/llama-4-scout-17b-16e-instruct",
          "displayName": "llama-4-scout-17b-16e-instruct",
          "enabled": true
        }
      ]
    },
    {
      "id": "ollama-cloud",
      "name": "Ollama Cloud",
      "enabled": true,
      "apiKey": "YOUR_OLLAMA_CLOUD_API_KEY",
      "endpoint": "https://ollama.com/v1",
      "models": [
        {
          "id": "gpt-oss:120b",
          "displayName": "gpt-oss:120b",
          "enabled": true
        },
        {
          "id": "deepseek-v3.2",
          "displayName": "deepseek-v3.2",
          "enabled": true
        },
        {
          "id": "kimi-k2.5",
          "displayName": "kimi-k2.5",
          "enabled": true
        }
      ]
    },
    {
      "id": "google-ai-studio",
      "name": "Google AI Studio",
      "enabled": true,
      "apiKey": "YOUR_GOOGLE_AI_STUDIO_API_KEY",
      "endpoint": "https://generativelanguage.googleapis.com/v1beta/openai",
      "models": [
        {
          "id": "gemini-2.5-flash",
          "displayName": "gemini-2.5-flash",
          "enabled": true
        },
        {
          "id": "gemini-3-flash-preview",
          "displayName": "gemini-3-flash-preview",
          "enabled": true
        },
        {
          "id": "gemini-2.5-pro",
          "displayName": "gemini-2.5-pro",
          "enabled": true
        }
      ]
    },
    {
      "id": "mistral",
      "name": "Mistral AI",
      "enabled": true,
      "apiKey": "YOUR_MISTRAL_API_KEY",
      "endpoint": "https://api.mistral.ai/v1",
      "models": [
        {
          "id": "mistral-small-latest",
          "displayName": "mistral-small-latest",
          "enabled": true
        },
        {
          "id": "open-mistral-nemo",
          "displayName": "open-mistral-nemo",
          "enabled": true
        },
        {
          "id": "codestral-latest",
          "displayName": "codestral-latest",
          "enabled": true
        },
        {
          "id": "magistral-small-latest",
          "displayName": "magistral-small-latest",
          "enabled": true
        }
      ]
    }
  ]
}

Cursor Docs

AI-powered code editor with custom model support

Quick Start

1

Get API Keys

Obtain an API key from each provider's console
2

Replace placeholders

Replace all YOUR_*_API_KEY values with your real keys
3

Place config file

Save to project root as .cursor-models
4

Restart Cursor

Restart the editor then select the custom model in the model picker

API Keys

Hugging Face Inference

Cloudflare Workers AI

Ollama Cloud

Google AI Studio

Mistral AI

Filename .cursor-models

Format toml

toml

# AIHubMix
[model.aihubmix.coding_glm_5_1_free]
name = "coding-glm-5.1-free"
api_base = "https://aihubmix.com/v1"
api_key = "YOUR_AIHUBMIX_API_KEY"

[model.aihubmix.coding_minimax_m2_7_free]
name = "coding-minimax-m2.7-free"
api_base = "https://aihubmix.com/v1"
api_key = "YOUR_AIHUBMIX_API_KEY"

# OpenRouter
[model.openrouter.glm_4_5_air_free]
name = "glm-4.5-air:free"
api_base = "https://openrouter.ai/api/v1"
api_key = "YOUR_OPENROUTER_API_KEY"

[model.openrouter.minimax_m2_5_free]
name = "minimax-m2.5:free"
api_base = "https://openrouter.ai/api/v1"
api_key = "YOUR_OPENROUTER_API_KEY"

# NVIDIA NIM
[model.nvidia-nim.llama_3_3_70b_instruct]
name = "llama-3.3-70b-instruct"
api_base = "https://integrate.api.nvidia.com/v1"
api_key = "YOUR_NVIDIA_NIM_API_KEY"

[model.nvidia-nim.deepseek_v4_pro]
name = "deepseek-v4-pro"
api_base = "https://integrate.api.nvidia.com/v1"
api_key = "YOUR_NVIDIA_NIM_API_KEY"

# Groq
[model.groq.llama_3_3_70b_versatile]
name = "llama-3.3-70b-versatile"
api_base = "https://api.groq.com/openai/v1"
api_key = "YOUR_GROQ_API_KEY"

[model.groq.llama_4_scout_17b_16e_instruct]
name = "llama-4-scout-17b-16e-instruct"
api_base = "https://api.groq.com/openai/v1"
api_key = "YOUR_GROQ_API_KEY"

# Cerebras
[model.cerebras.llama3_1_8b]
name = "llama3.1-8b"
api_base = "https://api.cerebras.ai/v1"
api_key = "YOUR_CEREBRAS_API_KEY"

[model.cerebras.qwen_3_235b_a22b_instruct_2507]
name = "qwen-3-235b-a22b-instruct-2507"
api_base = "https://api.cerebras.ai/v1"
api_key = "YOUR_CEREBRAS_API_KEY"

# Cohere
[model.cohere.command_a_03_2025]
name = "command-a-03-2025"
api_base = "https://api.cohere.ai/compatibility/v1"
api_key = "YOUR_COHERE_API_KEY"

[model.cohere.command_r_plus]
name = "command-r-plus"
api_base = "https://api.cohere.ai/compatibility/v1"
api_key = "YOUR_COHERE_API_KEY"

# Hugging Face Inference
[model.huggingface.Llama_3_3_70B_Instruct]
name = "Llama-3.3-70B-Instruct"
api_base = "https://router.huggingface.co/v1"
api_key = "YOUR_HUGGINGFACE_API_KEY"

[model.huggingface.DeepSeek_V3_0324]
name = "DeepSeek-V3-0324"
api_base = "https://router.huggingface.co/v1"
api_key = "YOUR_HUGGINGFACE_API_KEY"

# SambaNova Cloud
[model.sambanova.Meta_Llama_3_3_70B_Instruct]
name = "Meta-Llama-3.3-70B-Instruct"
api_base = "https://api.sambanova.ai/v1"
api_key = "YOUR_SAMBANOVA_API_KEY"

[model.sambanova.MiniMax_M2_5]
name = "MiniMax-M2.5"
api_base = "https://api.sambanova.ai/v1"
api_key = "YOUR_SAMBANOVA_API_KEY"

# GitHub Models
[model.github-models.gpt_4_1_mini]
name = "gpt-4.1-mini"
api_base = "https://models.github.ai/inference"
api_key = "YOUR_GITHUB_MODELS_API_KEY"

[model.github-models.llama_4_scout_17b_16e_instruct]
name = "llama-4-scout-17b-16e-instruct"
api_base = "https://models.github.ai/inference"
api_key = "YOUR_GITHUB_MODELS_API_KEY"

# ModelScope
[model.modelscope.Qwen3_30B_A3B_Instruct_2507]
name = "Qwen3-30B-A3B-Instruct-2507"
api_base = "https://api-inference.modelscope.cn/v1"
api_key = "YOUR_MODELSCOPE_API_KEY"

[model.modelscope.DeepSeek_V3_1]
name = "DeepSeek-V3.1"
api_base = "https://api-inference.modelscope.cn/v1"
api_key = "YOUR_MODELSCOPE_API_KEY"

# SiliconFlow
[model.siliconflow.Qwen3_8B]
name = "Qwen3-8B"
api_base = "https://api.siliconflow.com/v1"
api_key = "YOUR_SILICONFLOW_API_KEY"

[model.siliconflow.DeepSeek_R1_Distill_Qwen_7B]
name = "DeepSeek-R1-Distill-Qwen-7B"
api_base = "https://api.siliconflow.com/v1"
api_key = "YOUR_SILICONFLOW_API_KEY"

# BigModel
[model.bigmodel.glm_4_7_flash]
name = "glm-4.7-flash"
api_base = "https://open.bigmodel.cn/api/paas/v4"
api_key = "YOUR_BIGMODEL_API_KEY"

[model.bigmodel.glm_4_flash_250414]
name = "glm-4-flash-250414"
api_base = "https://open.bigmodel.cn/api/paas/v4"
api_key = "YOUR_BIGMODEL_API_KEY"

# Cloudflare Workers AI
[model.cloudflare-workers-ai.gpt_oss_120b]
name = "gpt-oss-120b"
api_base = "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1"
api_key = "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY"

[model.cloudflare-workers-ai.llama_3_3_70b_instruct_fp8_fast]
name = "llama-3.3-70b-instruct-fp8-fast"
api_base = "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1"
api_key = "YOUR_CLOUDFLARE_WORKERS_AI_API_KEY"

# Ollama Cloud
[model.ollama-cloud.gpt_oss_120b]
name = "gpt-oss:120b"
api_base = "https://ollama.com/v1"
api_key = "YOUR_OLLAMA_CLOUD_API_KEY"

[model.ollama-cloud.deepseek_v3_2]
name = "deepseek-v3.2"
api_base = "https://ollama.com/v1"
api_key = "YOUR_OLLAMA_CLOUD_API_KEY"

# Google AI Studio
[model.google-ai-studio.gemini_2_5_flash]
name = "gemini-2.5-flash"
api_base = "https://generativelanguage.googleapis.com/v1beta/openai"
api_key = "YOUR_GOOGLE_AI_STUDIO_API_KEY"

[model.google-ai-studio.gemini_3_flash_preview]
name = "gemini-3-flash-preview"
api_base = "https://generativelanguage.googleapis.com/v1beta/openai"
api_key = "YOUR_GOOGLE_AI_STUDIO_API_KEY"

# Mistral AI
[model.mistral.mistral_small_latest]
name = "mistral-small-latest"
api_base = "https://api.mistral.ai/v1"
api_key = "YOUR_MISTRAL_API_KEY"

[model.mistral.open_mistral_nemo]
name = "open-mistral-nemo"
api_base = "https://api.mistral.ai/v1"
api_key = "YOUR_MISTRAL_API_KEY"