PydanticAI

aid: pydantic-ai
name: PydanticAI
description: >
  PydanticAI is an open-source, model-agnostic Python agent framework built by
  the Pydantic team, designed to bring the ergonomic, type-safe design
  philosophy of FastAPI to production-grade generative AI application
  development. It provides structured outputs, dependency injection, and
  first-class support for leading model providers including OpenAI, Anthropic,
  Google Gemini, xAI, AWS Bedrock, Cohere, Mistral, Groq, and many more. The
  framework integrates seamlessly with Pydantic Logfire for OpenTelemetry-based
  observability, and includes pydantic-graph for complex agentic workflows,
  pydantic-evals for systematic agent evaluation, and clai for a CLI chat
  interface. PydanticAI is maintained by Pydantic, a London-based developer
  tooling company backed by Sequoia Capital, and forms a core part of their
  end-to-end AI engineering stack.
type: Index
image: https://kinlane-productions.s3.amazonaws.com/apis-json/apis-json-logo.jpg
tags:
  - AI
  - Agents
  - Python
  - LLM
  - Type Safety
  - Structured Outputs
  - Dependency Injection
  - OpenAI
  - Anthropic
  - Gemini
  - Observability
  - Framework
url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/apis.yml
created: '2026-06-12'
modified: '2026-06-12'
specificationVersion: '0.19'
apis:
  - aid: pydantic-ai:pydantic-ai-agent-framework
    name: PydanticAI Agent Framework
    description: >
      The core PydanticAI Python agent framework providing the Agent class,
      model provider integrations, tool registration, structured output
      validation, dependency injection, streaming, and durable execution
      capabilities for building production-grade GenAI applications.
    humanURL: https://pydantic.dev/docs/ai/overview/
    baseURL: https://pydantic.dev
    tags:
      - AI Agents
      - Python
      - LLM
      - Type Safety
    properties:
      - type: Documentation
        url: https://pydantic.dev/docs/ai/overview/
      - type: APIReference
        url: https://pydantic.dev/docs/ai/api/pydantic-ai/agent/
      - type: GettingStarted
        url: https://pydantic.dev/docs/ai/overview/install/
      - type: ModelProviders
        url: https://pydantic.dev/docs/ai/api/pydantic-ai/providers/
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/openapi/pydantic-ai-discovery-openapi.yml
      - type: JSONLDContext
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/json-ld/pydantic-ai-context.jsonld
      - type: Vocabulary
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/vocabulary/pydantic-ai-vocabulary.yml
  - aid: pydantic-ai:pydantic-logfire
    name: Pydantic Logfire
    description: >
      Pydantic Logfire is an OpenTelemetry-based observability platform with
      purpose-built features for LLM applications, including conversation
      panels, token tracking, cost monitoring, tool call inspection, and
      SQL-queryable production data. It also provides an AI Gateway for
      routing and FinOps management of model provider calls.
    humanURL: https://pydantic.dev/docs/logfire/
    baseURL: https://logfire.pydantic.dev
    tags:
      - Observability
      - OpenTelemetry
      - LLM
      - AI Gateway
      - FinOps
    properties:
      - type: Documentation
        url: https://pydantic.dev/docs/logfire/
      - type: Pricing
        url: https://pydantic.dev/pricing
      - type: StatusPage
        url: https://logfirestatus.pydantic.dev/
      - type: OpenAPI
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/openapi/pydantic-ai-logfire-openapi.yml
      - type: OpenAPISource
        url: https://logfire-us.pydantic.dev/api/openapi.json
      - type: JSONSchema
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/json-schema/logfire-project.json
      - type: JSONLDContext
        url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/json-ld/pydantic-ai-context.jsonld
common:
  - type: Website
    url: https://pydantic.dev/
  - type: Documentation
    url: https://pydantic.dev/docs/ai/overview/
  - type: GitHubOrganization
    url: https://github.com/pydantic
  - type: GitHubRepository
    url: https://github.com/pydantic/pydantic-ai
  - type: Blog
    url: https://pydantic.dev/articles
  - type: BlogIndex
    url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/blogs/blogs.json
  - type: Changelog
    url: https://pydantic.dev/docs/ai/changelog/
  - type: Pricing
    url: https://pydantic.dev/pricing
  - type: StatusPage
    url: https://logfirestatus.pydantic.dev/
  - type: LinkedIn
    url: https://www.linkedin.com/company/pydantic
  - type: X
    url: https://x.com/pydantic
  - type: PyPI
    url: https://pypi.org/project/pydantic-ai/
  - type: Plans
    url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/plans/pydantic-ai-plans-pricing.yml
  - type: RateLimits
    url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/rate-limits/pydantic-ai-rate-limits.yml
  - type: FinOps
    url: https://raw.githubusercontent.com/api-evangelist/pydantic-ai/refs/heads/main/finops/pydantic-ai-finops.yml
maintainers:
  - FN: Kin Lane
    email: [email protected]