If you're building with AI, you've probably dealt with this:

• One API key for OpenAI, another for Anthropic, another for Google
• Three billing dashboards, three SDKs, three different formats
• Switching models means rewriting integration code

There's a simpler way. This guide shows you how to access every major AI model through a single endpoint — in under 5 minutes.

The Problem#

Most AI providers use slightly different API formats. OpenAI has one format, Anthropic has another, Google has yet another. Even if you only use the OpenAI SDK, you still need separate keys and billing for each provider.

This creates real problems in production:

• Vendor lock-in: Your code is tied to one provider
• No failover: If OpenAI goes down, your app goes down
• Cost inefficiency: You can't easily route to the cheapest provider
• Key management overhead: More keys = more security surface

The Solution: API Aggregation#

An API aggregator sits between your code and the model providers. You send requests to one endpoint, and it routes them to the right provider. All through the OpenAI-compatible format you already know.

Step-by-Step Setup#

1. Create an Account#

Sign up at crazyrouter.com. You'll get $2 in free credits — enough for thousands of API calls to test with.

2. Get Your API Key#

After signing up, go to the API Tokens page and create a new key. It starts with sk-.

3. Update Your Code (2 Lines)#

Python:

import openai

client = openai.OpenAI(
 base_url="https://crazyrouter.com/v1", # Change this
 api_key="sk-your-crazyrouter-key" # Change this
)

# Everything else stays exactly the same
response = client.chat.completions.create(
 model="claude-opus-4-6",
 messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js:

const OpenAI = require('openai');

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

const response = await client.chat.completions.create({
 model: 'gpt-4o',
 messages: [{ role: 'user', content: 'Hello!' }]
});

cURL:

curl https://crazyrouter.com/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer sk-your-crazyrouter-key" \
 -d '{"model": "gemini-2.5-pro", "messages": [{"role": "user", "content": "Hello!"}]}'

That's it. Two lines changed, 300+ models unlocked.

4. Switch Models Freely#

Now you can switch between any model by changing the model parameter:

# Claude for complex reasoning
ask("Explain quantum computing", model="claude-opus-4-6")

# GPT for general tasks
ask("Write a product description", model="gpt-4o")

# Gemini for long context
ask("Summarize this 100-page document", model="gemini-2.5-pro")

# DeepSeek for cost-effective tasks
ask("Translate this to French", model="deepseek-v4")

No SDK changes. No format changes. Just swap the string.

Available Models#

300+ models total, continuously updated.

Pricing#

All models are available at 55% of official pricing:

Prices per 1M tokens (input / output)

Built-in Reliability#

Unlike calling providers directly, an aggregator gives you:

• Auto-failover: If one provider has issues, requests automatically route to a backup
• Smart routing: Requests go to the fastest available endpoint
• Rate limit handling: Aggregated rate limits are much higher than individual provider limits
• Zero downtime: Provider maintenance doesn't affect your app

Get Started#

1. Sign up — get $2 free credit
2. Change two lines of code
3. Access 300+ models at 45% savings

No contracts. No minimums. Pay only for what you use.