Pydantic Ai Model Integration

This walks you through wiring up different LLM providers in PydanticAI using simple string formats like `openai:gpt-4o` or `anthropic:claude-sonnet-4-5`. The fallback model setup is the standout feature: chain multiple providers so if one hits rate limits or goes down, it automatically tries the next. You also get streaming for both plain text and structured Pydantic output, per-run model settings overrides, and usage tracking that shows token counts across requests. Useful when you're building something that needs to stay up despite API hiccups or when you want to route cheaper requests to mini models and save the expensive ones for complex work.