API Documentation

Overview

MaxRouter is fully compatible with the OpenAI API format. You can use existing OpenAI SDKs, libraries, and tools with zero code changes — just swap the base URL and API key.

Base URL

Authentication

Pass your API key in the Authorization header:

# Using curl
curl https://api.silom.cn/llm-api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-5.4", "messages": [{"role": "user", "content": "Hello"}]}'

Chat Completions

Send a conversation and get a completion from the model.

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.silom.cn/llm-api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ]
)

print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
    baseURL: "https://api.silom.cn/llm-api/v1",
    apiKey: "YOUR_API_KEY"
});

const response = await client.chat.completions.create({
    model: "gpt-5.4",
    messages: [{ role: "user", content: "Hello!" }]
});

console.log(response.choices[0].message.content);

Streaming

Set stream: true to receive responses as Server-Sent Events (SSE).

from openai import OpenAI

client = OpenAI(
    base_url="https://api.silom.cn/llm-api/v1",
    api_key="YOUR_API_KEY"
)

stream = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Write a poem about the ocean"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Tool Calling

Define tools (functions) that the model can call. Compatible with OpenAI's function calling format.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.silom.cn/llm-api/v1",
    api_key="YOUR_API_KEY"
)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get current weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            },
            "required": ["location"]
        }
    }
}]

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools
)

Structured Output

Use response_format to get JSON output from the model.

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "List 3 programming languages with their use cases"}],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "languages",
            "schema": {
                "type": "object",
                "properties": {
                    "languages": {
                        "type": "array",
                        "items": {
                            "type": "object",
                            "properties": {
                                "name": {"type": "string"},
                                "use_case": {"type": "string"}
                            }
                        }
                    }
                }
            }
        }
    }
)

Available Models

See the Models & Pricing page for the full list with pricing.

Model List API

Get the list of available models programmatically:

curl https://api.silom.cn/llm-api/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Claude Code Setup

Connect Claude Code to MaxRouter for access to Claude Opus and Sonnet models.

Full Claude Code guide →

# Using CC Switch (recommended)
git clone https://github.com/farion1231/cc-switch.git
cd cc-switch && python3 cc_switch.py

# Or set environment variables manually
export ANTHROPIC_BASE_URL="https://api.silom.cn/llm-api"
export ANTHROPIC_API_KEY="YOUR_API_KEY"

Cursor Setup

Use MaxRouter with Cursor IDE for AI-powered coding.

Full Cursor guide →

1. Open Cursor Settings (Cmd+Shift+J / Ctrl+Shift+J)
2. Go to Models
3. Set Override OpenAI Base URL to https://api.silom.cn/llm-api/v1
4. Enter your API key

Cline Setup

Connect Cline (VS Code extension) to MaxRouter.

Full Cline guide →

1. Open Cline sidebar in VS Code
2. Click Settings
3. Select OpenAI Compatible
4. Base URL: https://api.silom.cn/llm-api/v1
5. Enter your API key and model name

Codex Setup

Use MaxRouter with OpenAI Codex CLI.

export OPENAI_BASE_URL="https://api.silom.cn/llm-api/v1"
export OPENAI_API_KEY="YOUR_API_KEY"

Error Codes

Rate Limits

• • Default: 60 requests/minute per API key
• • Default: 1M tokens/minute per API key
• • Enterprise plans with higher limits available — contact us