openrouter

Ensure you have installed the *official* `openrouter` package by OpenRouter: `pip install openrouter`

Set your OpenRouter API key as an environment variable named `OPENROUTER_API_KEY`. If using `python-dotenv`, ensure it's loaded. For direct client initialization, pass `api_key` explicitly. 

```python
import os
from openrouter import OpenRouter

# Ensure OPENROUTER_API_KEY is set in your environment or .env file
client = OpenRouter(api_key=os.getenv("OPENROUTER_API_KEY"))

# Or, if integrating with libraries like LiteLLM, ensure your .env has:
# OPENROUTER_API_KEY="your_api_key_here"
# OPENAI_API_BASE="https://openrouter.ai/api/v1"
```

This issue often requires updates within the `pydantic-ai` library or handling specific OpenRouter error responses. For immediate workarounds, consider trying different models, adjusting request parameters (e.g., streaming settings), or implementing custom error parsing if directly using the OpenRouter API without strict Pydantic AI validation. Check for newer versions of `pydantic-ai` or `openrouter` that might have addressed this compatibility. A potential fix involves using `OpenRouterModel` from `pydantic_ai.models.openrouter` if available, or catching `UnexpectedModelBehavior` and inspecting the raw response if possible.

Choose an OpenRouter model that explicitly supports tool use. You can check the OpenRouter documentation or model listings to identify models compatible with function calling. 

```python
from openrouter import OpenRouter

client = OpenRouter(api_key=os.getenv("OPENROUTER_API_KEY"))

response = client.chat.completions.create(
    model="openrouter/your-tool-use-compatible-model", # e.g., 'openai/gpt-4o' or other models listed as supporting tools
    messages=[
        {"role": "user", "content": "What's the weather like in Paris?"}
    ],
    tools=[
        # Your tool definitions here
    ]
)
```