API Reference

Complete API documentation for CPAI endpoints.

Base URL

http://localhost:8080/v1

All API requests require authentication via the Authorization header with a Bearer token.

Authentication

Include your API key in the Authorization header:

Authorization: Bearer cpai-xxxxx

Chat Completions

OpenAI-compatible chat completions endpoint.

POST /chat/completions

Request body:

{
  "model": "kimi-k2.5",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024,
  "stream": false
}

Response:

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "kimi-k2.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Streaming

Set stream: true for Server-Sent Events (SSE) streaming responses.

curl http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Models

Available models:

• kimi-k2.5 - Kimi K2.5 (default)
• deepseek-coder - DeepSeek Coder
• codellama - CodeLlama

Error Codes

Code	Description
400	Bad Request - Invalid request body
401	Unauthorized - Invalid or missing API key
403	Forbidden - IP not whitelisted
429	Too Many Requests - Concurrency limit exceeded
503	Service Unavailable - No GPU nodes available

Health Check

Public health endpoint (no authentication required):

GET /health