How OpenRouter Works

OpenRouter is an API gateway that gives you access to 300+ AI models from 60+ providers through a single endpoint and a single API key. It is OpenAI-compatible — meaning you change one line of code and your existing OpenAI calls work with any model in the catalog.

The Core Idea

Without OpenRouter, using multiple AI providers means managing multiple API keys, multiple client libraries, different request formats, different rate limits, and different billing accounts. OpenRouter abstracts all of that into one interface.

Using OpenRouter

OpenRouter's API is at https://openrouter.ai/api/v1 and uses the same request format as OpenAI. Change the base URL and API key:

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-your_openrouter_key",
)

# Use any model from the catalog — just change the model name
response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-6",   # Anthropic model via OpenRouter
    messages=[{"role": "user", "content": "Hello!"}]
)

# Or a Google model
response = client.chat.completions.create(
    model="google/gemini-2.5-pro",
    messages=[{"role": "user", "content": "Hello!"}]
)

# Or a free model
response = client.chat.completions.create(
    model="meta-llama/llama-3.2-3b-instruct:free",
    messages=[{"role": "user", "content": "Hello!"}]
)

Pricing

Model Naming Convention

OpenRouter model IDs follow provider/model-name. Free model variants are tagged with :free:

Checklist: Do You Understand This?

• Can you describe what OpenRouter does in one sentence?
• Can you make an OpenRouter API call using the OpenAI Python SDK?
• Do you know how to identify free vs paid models in the OpenRouter catalog?
• Do you understand how OpenRouter's 5.5% markup compares to direct provider pricing?