Agentic WeeklyGet the weekly
PydanticTested (smoke test)

Pydantic AI: what’s new and our verdict

Python agent framework built on Pydantic types, covering agents, realtime voice, image generation and embeddings.

Official site

Release Ruler for Pydantic AI: marked at its Tested release date on the timeline of every AI model we track.

At a glance

Evidence
Tested (smoke test)
Released
Oct 25, 2026
Last verified
Oct 25, 2026
Pricing
Official page, dated
Best for
agent building

Evidence and ranking

Evidence behind this verdict

  1. Sources read2 cited sources, latest fetched Oct 25, 2026. (done)
  2. Facts re-checkedLast verified Oct 25, 2026. (done)
  3. Run by usSmoke test on Oct 25, 2026 (scope below). (done)

Passed Test log result: Passed. Read the log

Where we rank it (editorial)

Listed here but not yet ranked. Ranks are editorial picks, not benchmark scores.

Pricing: Open-source library; costs come from the model APIs you call. (checked 2026-10-25)

Our verdict

Python agent framework built on Pydantic types, covering agents, realtime voice, image generation and embeddings.

Good for

  • Python teams that value type safety and validation

Skip if

  • You need a TypeScript framework

Tested. Tested 2026-10-25 (America/Chicago). Pydantic AI 2.61.0 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 3.7 s. Test environment: Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key. Agent tools were pointed at a local open-weight model (Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11), so we tested the tool, not any vendor's hosted models. Not tested: Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark. These are smoke tests, not a benchmark. Full log: /tests/pydantic-ai.

Full test log with exact commands, versions and raw output: Pydantic AI 2.61.0: our test log.

Evidence
Tested (smoke test, 2026-10-25, local 3B model (Qwen2.5-3B)). A smoke test is not a benchmark.
What we ran
Pydantic AI 2.61.0 passed our one-tool task on a local 3B model: 3 of 3 trials; cold uv install 3.7 s.
Model used
Qwen2.5-3B-Instruct (Q4_K_M) through Ollama 0.40.11
Environment
Linux x86_64 virtual machine (Debian 13), 8 vCPU, 15 GiB RAM, no GPU; no vendor account, login or API key
Not tested
Any vendor-hosted model: everything ran on a local 3B model, so tool-call reliability with frontier models is not measured here; Multi-agent flows, memory, long conversations, streaming, tracing and cloud deployment; Anything beyond one tool and one question; three trials is a smoke test, not a benchmark.
Date
(America/Chicago)

Best for

Key facts

Pydantic AI's docs describe typed control flow for agents across models, with agent capabilities and graph control flow as separate open-source packages. The repository is MIT-licensed.

  • License: MIT (per GitHub)
  • Platforms: Python
  • Pricing model: Free and open source
  • Free tier: Free to self-host
  • Paid plans: None listed for the library
  • GitHub: pydantic/pydantic-ai: 20,868 stars on 2026-10-25, last push 2026-10-26
  • Latest release we saw: 2026-10-25
  • How to start: pip install pydantic-ai and run the first agent from the docs.
  • Latest release we saw (2026-10-25): the newest release listed on the official page or repository when we read it on 2026-10-25.

How to set it up: Get started with Pydantic AI

These steps come from the vendor's own pages as read on 2026-10-25. We ran Pydantic AI on 2026-10-25; the test log lists what was and was not covered.

  1. Get access

    pip install pydantic-ai and run the first agent from the docs.

  2. Check the limits and costs first

    Free to self-host. Open-source library; costs come from the model APIs you call.

Pros and cons

Pros

  • Type-safe design
  • MIT license

Cons

  • Python only
  • Our test was one small task on a local 3B model; it does not show behaviour with hosted models or larger jobs

Alternatives and comparisons

  • LangChain: Open-source framework for building LLM applications and agents in Python and JavaScript, from the team behind LangGraph and LangSmith.
  • smolagents: Hugging Face's small Python library for agents that write and run code; the docs say the core logic fits in roughly a thousand lines.
  • OpenAI Agents SDK: Lightweight Python framework for multi-agent workflows, with tools, handoffs, sessions and tracing.
  • Langflow: MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.

FAQ

What is Pydantic AI?

Pydantic AI's docs describe typed control flow for agents across models, with agent capabilities and graph control flow as separate open-source packages. The repository is MIT-licensed.

Is Pydantic AI free?

Free to self-host. Open-source library; costs come from the model APIs you call. Checked 2026-10-25; prices change, so confirm on the vendor's page.

What license is Pydantic AI under?

Its license: MIT (per GitHub). Read from the project's own pages on 2026-10-25.

Sources

Last verified · Agentic Weekly

  • Langflow: MIT-licensed visual builder for AI agents and MCP servers with a very large GitHub following.
  • Botpress: Customer-support AI agent platform with a free plan and conversation-based paid plans.
  • Gumloop: Agent builder for teams; plans start at $37 per month with 20k included credits.

How to cite this page

Agentic Weekly, "Pydantic AI: what's new, verdict & setup", last updated 2026-10-25, https://theagenticweekly.com/tools/pydantic-ai

Keep the Reported or Tested label when you quote a verdict. Plain-text version: https://theagenticweekly.com/tools/pydantic-ai.md. More for AI assistants: /ai, /tools.json, /llms.txt.