Pydantic AI v2.68.0
Pydantic AI v2.68.0 released with conversation store, streamed cost for Google and Bedrock models, durable sub-agent delegations, and RefineOutput harness capability.
The Deploy Log | Products | Free, no signup
Pydantic AI changelog
19 versions of Pydantic AI from Pydantic in The Deploy Log. From to . On the median a new version every 3 days, publisher's dates only; the longest wait was 7 days. The newest is v2.68.0. 12 versions in the last 30 days. Each links the publisher's own page.
| Version | Publisher's date | Days after the one before |
|---|---|---|
| v2.68.0 | 2 | |
| v2.67.0 | 7 | |
| v2.65.0 | 6 | |
| v2.63.0 | 1 | |
| v2.62.0 | 3 | |
| v2.61.0 | 1 | |
| v2.60.0 | 2 | |
| v2.59.0 | 1 | |
| v2.58.0 | 4 | |
| v2.57.0 | 3 | |
| v2.56.0 | 4 | |
| v2.55.0 | 6 | |
| v2.54.0 | 1 | |
| v2.53.0 | 7 | |
| v2.51.0 | 0 | |
| v2.50.0 | ||
| v1.107.10 | 14 | |
| v1.107.9 | 1 | |
| v1.107.8 |
Pydantic AI v2.67.0
Pydantic AI v2.67.0 adds durable execution subagents, instruction file loading, and provider settings changes.
pydantic-ai v2.65.0
Added 12h prompt cache retention support for GPT-5.6 and later on OpenAI Responses API.
pydantic-ai v2.63.0
pydantic-ai v2.63.0 defaults CodeMode to dynamic_catalog=True and changes Gemini Live reconnect and Harness LLMReminder defaults.
Pydantic AI v2.62.0
Pydantic AI v2.62.0 adds mid-conversation thinking effort changes and new model error categories.
pydantic-ai v2.61.0
pydantic-ai v2.61.0 released with thinking override warnings and Cohere tool return handling.
Pydantic AI v2.60.0
Pydantic AI v2.60.0 released with model error categories, ModelSelectionContext fields, Bedrock maxTokens default, and deprecations.
Pydantic AI v2.59.0
Fixed GHSA-4whf-38hw-pxxh where attacker-controlled HTML in web_fetch could delay unrelated work.
Pydantic AI v2.58.0
Fixed MCP request telemetry exposure of server URLs, tokens, and headers in OpenTelemetry traces.
Pydantic AI v2.57.0
Pydantic AI v2.57.0 adds MetaProvider for Meta Muse models and updates realtime session handling.
Show the other 9 rows
Pydantic AI v2.56.0
Pydantic AI v2.56.0 adds Skills layering, ZaiProvider base_url, PGTaskDurability, and Render Workflows integration.
Pydantic AI v2.55.0
Pydantic AI v2.55.0 requires Python 3.11 or newer and adds durable execution for ExaSearch, YouSearch, and LocalStack tool requests.
Pydantic AI v2.54.0
Released pydantic-ai v2.54.0 with fixes for JSON schema, image generation, and durable execution.
Pydantic AI v2.53.0
Fixes a high-severity concurrency slot leak in ConcurrencyLimitedModel.
Pydantic AI v2.51.0
Adds OpenAI GPT-Live support with OpenAILiveModel and exposes context_window_used.
Pydantic AI v2.50.0
Adds DecisionModel and exposes OpenAI service_tier in provider details.
Pydantic AI v1.107.10
Pydantic AI v1.107.10 raises the remaining web_fetch timing bounds to 60 seconds.
Pydantic AI v1.107.9
Fixed GHSA-4whf-38hw-pxxh where attacker-controlled HTML in web_fetch could delay unrelated work.
Pydantic AI v1.107.8
Fixed MCP request telemetry exposure of server URLs, tokens, and headers in OpenTelemetry traces.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.