Tool Config Files

Generate ready-to-use LLM config files for all currently active free APIs

11 active providersCatalog last updated: · rev f109f5ff-ca5

LiteLLM uses the downloadable YAML directly. Other downloads are connection references for manual setup in each tool.

LiteLLM ProxyDocs

Unified LLM proxy supporting 100+ model routes

Quick Start

  1. 1

    Get API Keys

    Obtain an API key from each provider's console

  2. 2

    Replace placeholders

    Replace all YOUR_*_API_KEY values with your real keys

  3. 3

    Place config file

    Save as ./config.yaml

  4. 4

    Start the proxy

    Run litellm --config config.yaml

Filename litellm-config.yaml

Format yaml

yaml
# LiteLLM Proxy Configuration
# Catalog data as of 2026-11-20
# Includes 11 active providers

model_list:
  - model_name: "aihubmix/coding-glm-5.1-free"
    litellm_params:
      model: "openai/coding-glm-5.1-free"
      api_base: "https://aihubmix.com/v1"
      api_key: "YOUR_AIHUBMIX_API_KEY"
  - model_name: "aihubmix/kimi-for-coding-free"
    litellm_params:
      model: "openai/kimi-for-coding-free"
      api_base: "https://aihubmix.com/v1"
      api_key: "YOUR_AIHUBMIX_API_KEY"
  - model_name: "openrouter/ling-3.2-flash:free"
    litellm_params:
      model: "openai/inclusionai/ling-3.2-flash:free"
      api_base: "https://openrouter.ai/api/v1"
      api_key: "YOUR_OPENROUTER_API_KEY"
  - model_name: "openrouter/ernie-5.5-flash-preview:free"
    litellm_params:
      model: "openai/baidu/ernie-5.5-flash-preview:free"
      api_base: "https://openrouter.ai/api/v1"
      api_key: "YOUR_OPENROUTER_API_KEY"
  - model_name: "nvidia-nim/nemotron-3-ultra-550b-a55b"
    litellm_params:
      model: "openai/nvidia/nemotron-3-ultra-550b-a55b"
      api_base: "https://integrate.api.nvidia.com/v1"
      api_key: "YOUR_NVIDIA_NIM_API_KEY"
  - model_name: "nvidia-nim/glm-5.3-flash"
    litellm_params:
      model: "openai/z-ai/glm-5.3-flash"
      api_base: "https://integrate.api.nvidia.com/v1"
      api_key: "YOUR_NVIDIA_NIM_API_KEY"
  - model_name: "groq/gpt-oss-120b"
    litellm_params:
      model: "openai/openai/gpt-oss-120b"
      api_base: "https://api.groq.com/openai/v1"
      api_key: "YOUR_GROQ_API_KEY"
  - model_name: "groq/gpt-oss-20b"
    litellm_params:
      model: "openai/openai/gpt-oss-20b"
      api_base: "https://api.groq.com/openai/v1"
      api_key: "YOUR_GROQ_API_KEY"
  - model_name: "cohere/command-a-plus-05-2026"
    litellm_params:
      model: "openai/command-a-plus-05-2026"
      api_base: "https://api.cohere.ai/compatibility/v1"
      api_key: "YOUR_COHERE_API_KEY"
  - model_name: "cohere/command-a-03-2025"
    litellm_params:
      model: "openai/command-a-03-2025"
      api_base: "https://api.cohere.ai/compatibility/v1"
      api_key: "YOUR_COHERE_API_KEY"
  - model_name: "sambanova/DeepSeek-V3.1"
    litellm_params:
      model: "openai/DeepSeek-V3.1"
      api_base: "https://api.sambanova.ai/v1"
      api_key: "YOUR_SAMBANOVA_API_KEY"
  - model_name: "sambanova/Meta-Llama-3.3-70B-Instruct"
    litellm_params:
      model: "openai/Meta-Llama-3.3-70B-Instruct"
      api_base: "https://api.sambanova.ai/v1"
      api_key: "YOUR_SAMBANOVA_API_KEY"
  - model_name: "modelscope/Qwen3.5-35B-A3B"
    litellm_params:
      model: "openai/Qwen/Qwen3.5-35B-A3B"
      api_base: "https://api-inference.modelscope.cn/v1"
      api_key: "YOUR_MODELSCOPE_API_KEY"
  - model_name: "modelscope/Qwen3.5-27B"
    litellm_params:
      model: "openai/Qwen/Qwen3.5-27B"
      api_base: "https://api-inference.modelscope.cn/v1"
      api_key: "YOUR_MODELSCOPE_API_KEY"
  - model_name: "bigmodel/glm-4.7-flash"
    litellm_params:
      model: "openai/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: "openai/glm-4-flash-250414"
      api_base: "https://open.bigmodel.cn/api/paas/v4"
      api_key: "YOUR_BIGMODEL_API_KEY"
  - model_name: "google-ai-studio/gemini-4-hydrogen"
    litellm_params:
      model: "openai/gemini-4-hydrogen"
      api_base: "https://generativelanguage.googleapis.com/v1beta/openai"
      api_key: "YOUR_GOOGLE_AI_STUDIO_API_KEY"
  - model_name: "google-ai-studio/gemini-3.8-flash"
    litellm_params:
      model: "openai/gemini-3.8-flash"
      api_base: "https://generativelanguage.googleapis.com/v1beta/openai"
      api_key: "YOUR_GOOGLE_AI_STUDIO_API_KEY"
  - model_name: "agnes/agnes-2.5-flash"
    litellm_params:
      model: "openai/agnes-2.5-flash"
      api_base: "https://apihub.agnes-ai.com/v1"
      api_key: "YOUR_AGNES_API_KEY"
  - model_name: "agnes/agnes-3.0-flash"
    litellm_params:
      model: "openai/agnes-3.0-flash"
      api_base: "https://apihub.agnes-ai.com/v1"
      api_key: "YOUR_AGNES_API_KEY"
  - model_name: "amd/DeepSeek-V4-Flash"
    litellm_params:
      model: "openai/DeepSeek-V4-Flash"
      api_base: "https://developer.amd.com.cn/radeon/api/v1"
      api_key: "YOUR_AMD_API_KEY"
  - model_name: "amd/DeepSeek-V4.1-Flash"
    litellm_params:
      model: "openai/DeepSeek-V4.1-Flash"
      api_base: "https://developer.amd.com.cn/radeon/api/v1"
      api_key: "YOUR_AMD_API_KEY"

litellm_settings:
  drop_params: true
  set_verbose: false