English

CrazyRouter API Quick Start Guide

This article explains how to quickly integrate the Crazyrouter API, make your first call within 5 minutes, and use models such as OpenAI, Claude, Gemini, etc.

Crazyrouter Team

January 22, 2026 / 999 views

Crazyrouter

Open API Playground Open image tool Read the docs Check live pricing

Welcome to Crazyrouter! This guide will help you integrate the API within 5 minutes and start using world-class AI models.

Why choose Crazyrouter?#

Unified interface: Access 300+ AI models with a single API Key
OpenAI compatible: No code changes needed, just replace the base_url
Lower cost: More affordable than official pricing, pay-as-you-go with no subscription
High availability: Intelligent routing with automatic failover

1. Get your API Key#

Visit the Crazyrouter official site
Register an account and log in to the console
Go to the “Token Management” page
Click “Create Token”
Copy the generated API Key (starting with sk-)

Tip: Keep your API Key safe and do not expose it in public.

2. Make your first request#

Using curl#

bash

curl https://crazyrouter.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36" \
  -d '{
    "model": "gpt-5.2",
    "messages": [{"role": "user", "content": "Hello, how are you?"}],
    "temperature": 0.7
  }'

Using Python (recommended)#

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://crazyrouter.com/v1"
,
    default_headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }
)

response = client.chat.completions.create(
    model="gpt-5.2",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, how are you?"}
    ],
    temperature=0.7,
    max_tokens=1000
)

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

Using Node.js#

javascript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://crazyrouter.com/v1'
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'gpt-5.2',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Hello，Please introduce yourself' }
    ],
    temperature: 0.7
  });

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

main();

Streaming output#

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://crazyrouter.com/v1"
,
    default_headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }
)

stream = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role": "user", "content": "Write a poem about spring"}],
    stream=True
)

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

3. Supported models#

Crazyrouter supports 300+ AI models. Here are some popular ones:

Vendor	Model examples	Features
OpenAI	gpt-5.2, gpt-5, gpt-4o, o3-pro, o3-mini	Strong overall capability, supports multimodality
Anthropic	claude-opus-4.5, claude-4, claude-sonnet-4	Long context, strong coding ability
Google	gemini-3.0-pro, gemini-3-flash, gemini-2.5-pro	Multimodal with strong reasoning capability
xAI	grok-3, grok-3-mini, grok-3-vision	Real-time information and deep search
DeepSeek	deepseek-r1, deepseek-v3	High cost-performance, excellent Chinese support

View the full model list: Model Marketplace

4. Common parameter descriptions#

Parameter	Type	Description
`model`	string	Model name, e.g. `gpt-5.2`
`messages`	array	List of conversation messages
`temperature`	number	Randomness, 0–2, default 1
`max_tokens`	integer	Maximum number of output tokens
`stream`	boolean	Whether to use streaming output
`top_p`	number	Nucleus sampling parameter, 0–1

5. Error handling#

python

from openai import OpenAI, APIError, RateLimitError

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://crazyrouter.com/v1"
,
    default_headers={
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
    }
)

try:
    response = client.chat.completions.create(
        model="gpt-5.2",
        messages=[{"role": "user", "content": "Hello!"}]
    )
except RateLimitError:
    print("Too many requests. Please try again later.")
except APIError as e:
    print(f"API error: {e}")