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

🐛 Bug Fixes

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

New Contributors

• @glendigity made their first contribution in #5791
• @Oxygen56 made their first contribution in #5809
• @HaozheZhang6 made their first contribution in #5904
• @ret2libc made their first contribution in #5845
• @cooleryu made their first contribution in #5443
• @jjmllr made their first contribution in #5441
• @strickvl made their first contribution in #5908
• @Julien-ser made their first contribution in #5833
• @MylittleQueercat made their first contribution in #5876
• @Kropiunig made their first contribution in #5928
• @Nukually made their first contribution in #5813
• @MakenRosa made their first contribution in #5997
• @manan-tech made their first contribution in #5978
• @MeloMei made their first contribution in #5950
• @kaxil made their first contribution in #5984
• @pranavmutatkar made their first contribution in #5991
• @Ghraven made their first contribution in #5971
• @bdpgmbv made their first contribution in #5957

Full Changelog: v2.0.0b7...v2.0.0