> ## Documentation Index
> Fetch the complete documentation index at: https://thethirdpenco-feat-tool-lifecycle-events.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenRouter

> Use any AI model through OpenRouter's unified API

OpenRouter provides access to many AI models from different providers through a single, unified API. This makes it easy to switch between models without changing your code.

## Setup

Set your API key as an environment variable:

```bash theme={null}
export OPENROUTER_API_KEY="sk-or-v1-..."
```

Get your API key from [OpenRouter](https://openrouter.ai/keys).

## Usage

```python theme={null}
from ai_query import generate_text
from ai_query.providers import openrouter

result = await generate_text(
    model=openrouter("openai/gpt-4o"),
    prompt="Explain machine learning in simple terms."
)
```

## Available Models

OpenRouter provides access to models from many providers. Model IDs follow the pattern `provider/model-name`:

| Model ID                             | Description                 |
| ------------------------------------ | --------------------------- |
| `openai/gpt-4o`                      | OpenAI GPT-4o               |
| `openai/gpt-4o-mini`                 | OpenAI GPT-4o mini          |
| `anthropic/claude-3.5-sonnet`        | Anthropic Claude 3.5 Sonnet |
| `anthropic/claude-3-opus`            | Anthropic Claude 3 Opus     |
| `google/gemini-pro-1.5`              | Google Gemini Pro 1.5       |
| `meta-llama/llama-3.1-405b-instruct` | Meta Llama 3.1 405B         |
| `mistralai/mistral-large`            | Mistral Large               |

See the [OpenRouter models page](https://openrouter.ai/models) for a full list.

## Provider Options

Customize parameters:

````python theme={null}
result = await generate_text(
    model=openrouter("anthropic/claude-3.5-sonnet"),
    prompt="Write a creative story.",
    provider_options={
        "openrouter": {
            "temperature": 0.9,
            "max_tokens": 1000
        }
    }
)

## Tool Calling

Tool calling works the same as with other providers:

```python
from ai_query import generate_text
from ai_query.providers import openrouter, tool, Field

@tool(description="Search the web")
async def search(query: str = Field(description="Search query")) -> str:
    return f"Results for: {query}"

result = await generate_text(
    model=openrouter("openai/gpt-4o"),
    prompt="Search for the latest Python news",
    tools={"search": search}
)
````

## Streaming

```python theme={null}
from ai_query import stream_text
from ai_query.providers import openrouter

result = stream_text(
    model=openrouter("openai/gpt-4o"),
    prompt="Write a poem about coding."
)

async for chunk in result.text_stream:
    print(chunk, end="", flush=True)
```

## Why OpenRouter?

* **Single API**: Access models from OpenAI, Anthropic, Google, Meta, and more through one API
* **Fallback routing**: Automatically fall back to alternative models if one is unavailable
* **Cost optimization**: Compare prices across providers
* **No vendor lock-in**: Easily switch between models without code changes