中文文档

Convert ChatJimmy into an OpenAI-compatible API. Deploy to Vercel Edge in one click.

1. Fork this repository
2. Click the button below to deploy your fork to Vercel

• OpenAI-compatible API — GET /v1/models and POST /v1/chat/completions
• Streaming & non-streaming — full SSE streaming support
• Bearer token auth — optional API key protection via API_KEY env var
• Vercel Edge — runs on Vercel Edge Runtime with Hono
• Zero config — auto-detected by Vercel CLI, ready to deploy

Set your deployed URL as the API base and use it like OpenAI:

curl https://your-deploy.vercel.app/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer your-api-key" \
  -d '{
    "model": "llama3.1-8B",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Works with any OpenAI-compatible client:

from openai import OpenAI

client = OpenAI(
    base_url="https://your-deploy.vercel.app/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="llama3.1-8B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

MIT