Why use PydanticAI

Built by the Pydantic Team: Built by the team behind Pydantic (the validation layer of the OpenAI SDK, the Anthropic SDK, LangChain, LlamaIndex, AutoGPT, Transformers, CrewAI, Instructor and many more).

Model-agnostic: Supports OpenAI, Anthropic, Gemini, Deepseek, Ollama, Groq, Cohere, and Mistral, and there is a simple interface to implement support for other models.

Pydantic Logfire Integration: Seamlessly integrates with Pydantic Logfire for real-time debugging, performance monitoring, and behavior tracking of your LLM-powered applications.

Type-safe: Designed to make type checking as powerful and informative as possible for you.

Python-centric Design: Leverages Python's familiar control flow and agent composition to build your AI-driven projects, making it easy to apply standard Python best practices you'd use in any other (non-AI) project.

Structured Responses: Harnesses the power of Pydantic to validate and structure model outputs, ensuring responses are consistent across runs.

Dependency Injection System: Offers an optional dependency injection system to provide data and services to your agent's system prompts, tools and output validators. This is useful for testing and eval-driven iterative development.

Streamed Responses: Provides the ability to stream LLM responses continuously, with immediate validation, ensuring real time access to validated outputs.