Pydantic-AI v2.38.1 Adds Gemini/Claude Models, vLLM Support, and Context Window Features
Pydantic-AI v2.38.1 introduces support for new large language models, including `gemini-3.8-flash`, Claude Fable 5.1, and Claude Mythos 5.1, alongside a new `VLLMProvider` for vLLM servers. This release also adds `context_window` management features to `ModelProfile` and enables application code to emit typed custom events into the run stream. It includes several bug fixes, particularly around tool call handling and provider interactions, while also noting a compatibility change for one-off capabilities. These updates enhance the framework's AI integration capabilities and address various operational issues for developers.
- →Add context_window to ModelProfile and context_window_used to RunContext by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/4611
- →Add profile flag to reject streams without finish_reason by @jonashaag in https://github.com/pydantic/pydantic-ai/pull/7096
- →Add gemini-3.8-flash model by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/8021
- →Add VLLMProvider for vLLM servers by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/6153
- →Support CancellationToken in UI adapter run methods by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7743
Features (6) ›
- Add context_window to ModelProfile and context_window_used to RunContext by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/4611
- Add profile flag to reject streams without finish_reason by @jonashaag in https://github.com/pydantic/pydantic-ai/pull/7096
- Add gemini-3.8-flash model by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/8021
Let application code and capabilities emit typed CustomEvents and CapabilityEvents into the run event stream and subscribe with @on_event by @DouweM in https://github.com/pydantic/pydantic-ai/pull/6258
Add Claude Fable 5.1 (claude-fable-5-1) and Claude Mythos 5.1 (claude-mythos-5-1) support by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7989
- Add VLLMProvider for vLLM servers by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/6153
Fixes (12) ›
- Support CancellationToken in UI adapter run methods by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7743
Stop pytest tests/durable_exec/temporal from crashing when the suite's requirements are missing by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7898
Fix DeepSeek and Together forced tool_choice handling and support NativeOutput on DeepSeek's Responses API by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7450
- Restore raw tool-call IDs when replaying Bedrock Mantle Responses history by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7962
- Keep a run cancelled during its first tool call resumable by @DouweM in https://github.com/pydantic/pydantic-ai/pull/7993
Fix CodeExecutionTool uploads never reaching a fresh Anthropic container on a multi-turn history by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7864
- Prevent synthetic reasoning IDs from reaching OpenAI Responses by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/8020
- Emit REASONING_* events from ag-ui-protocol 0.1.11 instead of 0.1.13 by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/7226
- Accept the environment-key call pattern in GoogleProvider's overload by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/8030
Fix XaiModel streamed text after a native tool call being merged into the ended pre-call part by @pydanty in https://github.com/pydantic/pydantic-ai/pull/7925
- Persist Anthropic stale thinking-block recovery across turns by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/8037
Preserve dynamic native factory config in XSearch and ImageGeneration fallback subagents by @CoralGarden52 in https://github.com/pydantic/pydantic-ai/pull/7541
Maintenance (1) ›
- Bump genai-prices to 0.1.6 by @adtyavrdhn in https://github.com/pydantic/pydantic-ai/pull/8019
https://github.com/pydantic/pydantic-ai/releases/tag/v2.38.1
Related releases
- Pydantic-AI v2.38.0 Adds New Gemini and Claude Models, VLLM Provider, and Event Streaming Pydantic AI Releases ·
- pydantic-ai v2.37.0 Adds glm-5.3-flash Support and Bug Fixes Pydantic AI Releases ·
- Pydantic AI 2.36.0 Release Introduces Durable Operations and Tool-Call Streaming Pydantic AI Releases ·
- Pydantic-AI v2.35.3 Patch Release Addresses Several Bug Fixes Pydantic AI Releases ·
- pydantic-ai v2.35.2 Patches GLM Routing and Tooling Issues Pydantic AI Releases ·
- Google ADK Python v1.39.1 Patch Addresses Numerous Fixes Google ADK (Python) Releases ·