README.md

---
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

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

```bash
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):

```bash
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:

```bash
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"}]
  }'
```