SinoRouter API Docs

Quickstart

Use SinoRouter with an OpenAI-compatible API format. Replace the base URL and model name, then send requests with your API key.

Base URL: https://api.sinorouter.ai/v1

Authentication

Pass your API key in the Authorization header.

Authorization: Bearer YOUR_API_KEY

Chat Completions

Send text and reasoning workloads through the chat completions endpoint.

curl https://api.sinorouter.ai/v1/chat/completions \
      -H "Authorization: Bearer YOUR_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "deepseek-v4-pro",
        "messages": [
          {
    "role": "user",
    "content": "Summarize this customer support ticket."
          }
        ]
      }'

const response = await fetch("https://api.sinorouter.ai/v1/chat/completions", {
      method: "POST",
      headers: {
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
      },
      body: JSON.stringify({
        model: "deepseek-v4-pro",
        messages: [
          { role: "user", content: "Write a product description." }
        ]
      })
    });

import requests

    response = requests.post(
        "https://api.sinorouter.ai/v1/chat/completions",
        headers={
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
        },
        json={
    "model": "deepseek-v4-pro",
    "messages": [
        {"role": "user", "content": "Summarize this document."}
    ],
        },
    )

Model List

List available models for your account. Enterprise availability may depend on your contract and routing setup.

GET /v1/models

Image & Video

Media generation endpoints may use model-specific parameters such as size, duration, resolution, frame rate, and quality mode.

POST /v1/images/generations
    POST /v1/videos/generations

Errors

SinoRouter uses standard HTTP status codes for request failures, authentication issues, quota limits, and provider-side errors.

Rate Limits

Self-serve accounts and enterprise accounts may have different limits. Enterprise customers can request dedicated limits based on usage volume and workload type.