AI Nexus API Reference

Overview

AI Nexus provides an OpenAI-compatible API for all Chinese AI models. If you've used OpenAI's API, you already know how to use ours. Simply change the base URL and API key.

Base URL

Authentication

Include your API key in the Authorization header:

Authorization: Bearer sk-ai-nexus-xxxxxxxx

Supported Models

We support all models listed on our Models page. Use the model ID as the model parameter in your requests.

Chat Completions

Create a chat completion. Identical to the OpenAI chat completions API.

Request Body

{
  "model": "deepseek-v4",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1718000000,
  "model": "deepseek-v4",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 10,
    "total_tokens": 35
  }
}

Streaming

Set stream: true in your request to receive Server-Sent Events (SSE). Each event contains a delta with partial content.

{
  "model": "qwen-max",
  "messages": [{"role": "user", "content": "Tell me a story"}],
  "stream": true
}

Streaming responses use the same format as OpenAI's streaming API.

Parameters

List Models

Returns a list of all available models. Response format is identical to OpenAI's model list.

{
  "object": "list",
  "data": [
    {"id": "deepseek-v4", "object": "model", "created": 1718000000, "owned_by": "ai-nexus"},
    {"id": "deepseek-v4-flash", "object": "model", ...},
    {"id": "qwen-max", "object": "model", ...}
  ]
}

Check Balance

Check your account balance and usage statistics.

{
  "balance": 42.50,
  "currency": "USD",
  "total_spent": 157.30,
  "last_updated": "2025-06-17T12:00:00Z"
}

Error Codes

Rate Limits

Rate limits vary by plan. Free tier: 10 RPM. Paid plans scale with usage. Contact us for dedicated throughput.