Overview

The StarUnion open platform exposes standard HTTP API endpoints and works with a wide range of languages and environments. The API is compatible with the OpenAI SDK — just point base_url at StarUnion to migrate an existing app with no other changes.

API Endpoint

The platform's base API endpoint is:

All API requests must use HTTPS. Resource-based paths are appended to the Base URL above, e.g. /chat/completions.

Authentication

The StarUnion API uses Bearer Token authentication. Add an Authorization header with the value Bearer YOUR_API_KEY to each request.

curl https://www.starunion.net/v1/models \
  -H "Authorization: Bearer $API_KEY"

First Call

The example below shows how to generate a chat reply with doubao-seed-2-0-lite-260215. All snippets are verified to run as-is — just replace YOUR_API_KEY with your real key.

curl -X POST "https://www.starunion.net/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "doubao-seed-2-0-lite-260215",
    "messages": [
      {"role": "system", "content": "You are a professional AI assistant."},
      {"role": "user", "content": "Hi, please introduce yourself."}
    ],
    "temperature": 1.0,
    "stream": false
  }'

Response Format

Every Chat Completions response follows the OpenAI JSON schema, so existing ecosystem tooling works out of the box:

{
  "id": "chatcmpl-7xN3f2k...",
  "object": "chat.completion",
  "created": 1708502400,
  "model": "doubao-seed-2-0-lite-260215",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! I'm the AI assistant served through StarUnion..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 142,
    "total_tokens": 170
  }
}

Error Handling

When a request fails, the API returns a non-2xx HTTP status code and a JSON error body containing code and message fields. See the Error Codes section for details.

• 401 Unauthorized — API Key missing or invalid
• 429 Too Many Requests — rate limit hit; use exponential backoff retries
• 500 Internal Server Error — platform-side error; contact support with the request-id