API Documentation

Learn how to configure your applications to call Unces API endpoints.

Connection Settings

Base URL

https://api.unces.xyz/v1

Authorization Header

Authorization: Bearer sk-unc-...

OpenAI Compatibility

Our API proxy strictly adheres to the official OpenAI Chat Completions payload specification. All standard parameters like temperature, stream, max_tokens, and stop sequences are fully supported.

Rate Limits

Free Tier: 10 requests per minute (RPM) / 100K tokens per minute (TPM).
Paid Tier: Up to 60 requests per minute (RPM) after credit top-up.

curl https://api.unces.xyz/v1/chat/completions \
  -H "Authorization: Bearer $UNCES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwepus-35b-a3b",
    "messages": [
      {"role": "user", "content": "Write a python server to proxy LiteLLM logs"}
    ],
    "stream": true
  }'

Retrieve Model List via API

You can programmatically fetch all active models and their properties by querying our model listing endpoint.

GET https://api.unces.xyz/v1/models