README.md

metadata

title: LiteLLM Proxy
sdk: docker
app_port: 7860
pinned: false

LiteLLM Proxy (OpenAI-Compatible)

This Space runs the LiteLLM proxy, providing an OpenAI-compatible API that can route to multiple providers.

Secrets to Set (Space Settings -> Secrets)

• LITELLM_MASTER_KEY: master key required in Authorization: Bearer ...
• GMN_API_KEY: for the third-party OpenAI-compatible gateway
• GMN_API_BASE: set to https://gmn.chuangzuoli.com/v1
• ANTHROPIC_API_KEY: for Anthropic routing
• ARK_ANTHROPIC_BASE_URL: set to https://ark.cn-beijing.volces.com/api/coding
• ARK_ANTHROPIC_AUTH_TOKEN: Volcengine ARK API key (Anthropic-compatible)

Useful Endpoints

• GET /health/liveliness (no auth) - good for keep-alive pings
• POST /chat/completions (auth) - OpenAI-compatible chat completions
• POST /v1/responses (auth) - OpenAI-compatible Responses API (recommended)

Example Curl

curl -sS https://YOUR-SPACE.hf.space/health/liveliness

curl -sS https://YOUR-SPACE.hf.space/chat/completions \
  -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Say hi"}]
  }'

Responses API (some gateways require this exact path + OpenAI-Beta header):

curl -sS https://YOUR-SPACE.hf.space/v1/responses \
  -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -H "OpenAI-Beta: responses=v1" \
  -d '{
    "model": "gpt-4o-mini",
    "input": "Say hi"
  }'

Anthropic via alias:

curl -sS https://YOUR-SPACE.hf.space/chat/completions \
  -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet",
    "messages": [{"role": "user", "content": "Say hi from Claude"}]
  }'