Sourced from pydantic-ai-slim[google,openai]'s releases.

v2.0.0 (2026-06-23)

🎉 Pydantic AI V2.0 is here!

After seven betas, Pydantic AI V2 is now stable. V2 leans into a harness-first design with capabilities as a core primitive — a single composable unit that bundles an agent's tools, hooks, instructions, and model settings, reaching every layer of the agent through one concept.

Install it with:

uv add pydantic-ai

See the Upgrade Guide for everything that's changed and the recommended path from V1.

---

What's Changed

🚀 Features

• Add gemini-embedding-2 embedding model by @​dsfaccini in pydantic/pydantic-ai#5887
• Map AG-UI interrupts to DeferredTools in AGUIAdapter by @​jjmllr in pydantic/pydantic-ai#5441
• Add google_task text-prefix conditioning for gemini-embedding-2 embeddings by @​dsfaccini in pydantic/pydantic-ai#5894
• feat: add xai_max_turns to XaiModelSettings by @​manan-tech in pydantic/pydantic-ai#5978
• Pydantic AI V2 by @​DouweM in pydantic/pydantic-ai#5451

🐛 Bug Fixes

• Don't send Gemini function_calling_config without function declarations by @​glendigity in pydantic/pydantic-ai#5791
• fix(openai): map image UploadedFile parts to input_image by @​Oxygen56 in pydantic/pydantic-ai#5809
• Fix unified thinking handling for Groq qwen3 and Cerebras gpt-oss by @​dsfaccini in pydantic/pydantic-ai#5850
• Disallow non-finite Evaluator outputs by @​alexmojaki in pydantic/pydantic-ai#5863
• Fix AnthropicModel.count_tokens divergence on ToolSearchTool replay history by @​dsfaccini in pydantic/pydantic-ai#5855
• Send reasoning_content on synthesized tool-call turns for DeepSeek thinking models by @​adtyavrdhn in pydantic/pydantic-ai#5842
• Validate UploadedFile.provider_name in tool returns and consolidate the guard into Model._validate_uploaded_file_provider by @​Oxygen56 in pydantic/pydantic-ai#5860
• Replay Cerebras zai-glm reasoning in <think> tags and bump to zai-glm-4.7 by @​dsfaccini in pydantic/pydantic-ai#5891
• Retain dropped usage fields across GoogleModel streaming chunks by @​dsfaccini in pydantic/pydantic-ai#5886
• Accumulate output_audio_tokens in RunUsage by @​HaozheZhang6 in pydantic/pydantic-ai#5904
• fix(output): validate union kind discriminator in text output by @​ret2libc in pydantic/pydantic-ai#5845
• fix(openai): prevent AG-UI stalls during multi-server MCP discovery by @​cooleryu in pydantic/pydantic-ai#5443
• Forward additionalModelRequestFields in Bedrock count_tokens by @​dsfaccini in pydantic/pydantic-ai#5910
• Fix MCPToolset(http_client=...) crash on FastMCP's follow_redirects kwarg by @​he-yufeng in pydantic/pydantic-ai#5694
• fix(cohere): forward tool_choice from ModelSettings to v2 chat API by @​Julien-ser in pydantic/pydantic-ai#5833
• Route max_tokens to max_completion_tokens or max_tokens via OpenAIModelProfile flag by @​dsfaccini in pydantic/pydantic-ai#5926
• Forward top_k model setting to Bedrock additionalModelRequestFields by @​dsfaccini in pydantic/pydantic-ai#5922
• Fix FallbackModel declaring an unassigned _model_name dataclass field by @​dorukgezici in pydantic/pydantic-ai#5932
• fix(groq): add groq_reasoning_effort setting by @​Oxygen56 in pydantic/pydantic-ai#5797
• fix: use running loop in chat app example by @​Ghraven in pydantic/pydantic-ai#5971
• fix(cohere): forward usage.cached_tokens as cache_read_tokens by @​bdpgmbv in pydantic/pydantic-ai#5957
• fix(mistral): forward penalties in completions by @​he-yufeng in pydantic/pydantic-ai#5695
• Emit reasoning_effort='none' for Cerebras, deprecate cerebras_disable_reasoning, add cerebras_clear_thinking by @​dsfaccini in pydantic/pydantic-ai#5897

New Contributors

• @​glendigity made their first contribution in pydantic/pydantic-ai#5791

... (truncated)

Sourced from pydantic-ai-slim[google,openai]'s changelog.

v2.0.0 (2026-06-23)

The stable V2.0 release. There are no new breaking or behavior changes since the betas; the full breaking-change list and recommended upgrade path are in the v2.0.0b1 entry below. Install it with:

uv add pydantic-ai

v2.0.0b7 (2026-06-10)

The seventh V2 beta, forked from v1.107.0. There are no new V2 breaking or behavior changes since v2.0.0b6 below — everything in that entry applies unchanged — but this beta picks up the latest V1 release on top, which adds Claude Fable 5 / Mythos 5 model support and OpenRouter prompt caching (CachePoint), plus known_model_names() and Anthropic fixes; see the v1.107.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

pip/uv-add "pydantic-ai==2.0.0b7"

For the full breaking-change list and the recommended upgrade path, see the v2.0.0b1 entry below; the only difference is that the latest V1 to upgrade through first is now v1.107.0.

v2.0.0b6 (2026-06-04)

The sixth V2 beta, forked from v1.106.0. There are no new V2 breaking or behavior changes since v2.0.0b5 below — everything in that entry applies unchanged — but this beta picks up the latest V1 release on top, which adds api_host/timeout configuration and base seed mapping for the xAI provider, plus streaming and data-URI handling fixes; see the v1.106.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

pip/uv-add "pydantic-ai==2.0.0b6"

For the full breaking-change list and the recommended upgrade path, see the v2.0.0b1 entry below; the only difference is that the latest V1 to upgrade through first is now v1.106.0.

v2.0.0b5 (2026-06-02)

The fifth V2 beta, forked from v1.105.0. There are no new V2 breaking or behavior changes since v2.0.0b4 below — everything in that entry (including the prepare-callbacks change) still applies — but this beta picks up the latest V1 release on top, which adds on-demand (deferred-loading) capabilities and Grok 4.3 reasoning_effort support, plus GoogleModelSettings.google_cached_content and Temporal gateway/ fixes; see the v1.105.0 release notes for the full list.

Install it the same way, pinning the exact pre-release version:

pip/uv-add "pydantic-ai==2.0.0b5"

For the full breaking-change list and the recommended upgrade path, see the v2.0.0b1 entry below; the only difference is that the latest V1 to upgrade through first is now v1.105.0.

v2.0.0b4 (2026-05-28)

The fourth V2 beta, forked from v1.104.0. One new V2 behavior change since v2.0.0b3:

• Prepare callbacks (prepare_tools= / PrepareTools capability) that return None now raise TypeError instead of silently stripping all tools. V1.103.0 announces this change via PydanticAIDeprecationWarning (see #5188); V2 turns the warning into a hard error (see #5668). Return an empty list ([]) when you mean "no tools for this turn."

... (truncated)

• e19e180 docs: de-beta the Upgrade Guide and Version Policy for the stable v2.0 releas...
• e2b661c Pydantic AI V2 (#5451)
• 61c71f0 Emit reasoning_effort='none' for Cerebras, deprecate `cerebras_disable_reas...
• 3e83d4c Fix broken xAI and ACI.dev doc links (#6020)
• a249886 Add scheduled lychee workflow to check docs links (#6018)
• 46c6a61 docs: fix broken temporalio API reference links (#5740)
• 82a484d fix(mistral): forward penalties in completions (#5695)
• adfec3a fix(cohere): forward usage.cached_tokens as cache_read_tokens (#5957)
• e59f24e Make retry-after transport test deterministic (#5533)
• de3a512 fix: use running loop in chat app example (#5971)
• Additional commits viewable in compare view