OpenAI’s official Python library for building applications that use the OpenAI API. Useful for developers who want to authenticate and make API requests from Python.
Project status
- Actively maintained, with the upstream GitHub activity showing the last push was 2026-07-29, and multiple recent
openai-pythonupdate tags in late July 2026. - Update cadence appears steady and frequent, about every 1 to 8 days across the most recent set (2026-07-09 to 2026-07-28), suggesting an ongoing development and release process.
AI summary generated
Recent updates
v2.53.0
v2.53.0 adds support for the gpt-5.5 model and extends Responses tool-call typing to include the tool output’s name and namespace. The release notes also mention a CI fix to avoid NumPy source builds and duplicate HTTPX coverage.
Featuresv2.52.1
Release v2.52.1 updates the package version metadata and adjusts CI configuration. The only functional change called out in the release notes is a CI workflow pin for setup-uv v5.
v2.52.0
v2.52.0 adds a new content provenance checks API (with both sync and async client support) and introduces better retry handling for server-directed Retry-After delays, extending the honored window to up to two minutes. It also updates documentation with new API-key mTLS HTTP client recipes.
Featuresv2.51.0
This release (v2.51.0) extends the existing `service_tier` parameter to accept a new value, `fast`, and updates request/response typing across chat completions and responses APIs. Release notes mention adding the fast tier and wiring it into helper methods, but the code diff contains additional behavioral documentation not present in the notes.
Featuresv2.50.0
v2.50.0 updates transcription-related API surface and models. The release notes call out a transcription keyword overload fix, plus general transcription model updates.
Featuresv2.49.0
v2.49.0 raises the supported Python floor to 3.10 (from 3.9) and adds automation to continuously review and validate Python version support. The release also introduces new CI workflows and scripts to enforce wheel metadata and version-policy consistency, and updates internal tooling and dependency lockfiles accordingly.
BreakingFeaturesv2.48.0
v2.48.0 adds new admin endpoints for managing hard spend limits at both the organization and project level, and updates client typings so `prompt_cache_key` and `safety_identifier` can be passed as `None`. The diff also includes several type and documentation updates around reasoning context defaults and error codes.
Featuresv2.47.0
v2.47.0 adds experimental runtime support for HTTPX2 clients, along with internal normalization and exception-handling changes needed to make HTTPX2 clients work with the SDK. It also updates CI tooling/workflows and tightens the aiohttp dependency requirement for Python 3.10+.
Featuresv2.46.0
v2.46.0 adds new organization admin API support for service account API keys and introduces filtering by owner project access. The release also updates several generated types, including usage response schemas and audit log event type filters.
Featuresv2.45.0
v2.45.0 is a small release in the notes, highlighting an update to the gpt-5.6-sol API integration, and a bug fix restoring beta resource accessors. The actual diff is much larger, with substantial additions to beta type exports and internal response parsing improvements.
v2.44.0
Release v2.44.0 notes only mention a small auth bug fix, prioritizing the first auth header. The actual diff, however, includes a much larger internal refactor centered on Bedrock authentication plus a new provider abstraction that changes how authentication and base URL routing are configured.
v2.43.0
v2.43.0 primarily reflects an OpenAPI/Stainless regeneration. The only substantive code change visible in the diff is the addition of support for a Secure MCP Tunnel option via a new `tunnel_id` field in multiple MCP tool/config type definitions.
Featuresv2.42.0
v2.42.0 adds new admin capabilities and expands several typed API surfaces. The main functional changes visible in the diff include new admin spend alert retrieval endpoints and new support for expiring admin API keys, plus expanded audit log filtering and additional audit event detail types.
Featuresv2.41.1
Release v2.41.1 contains only build and release-process related changes, plus the expected version bump to 2.41.1. The published release notes mention only removal of the scheduled workflow trigger, but the code diff shows a larger refactor of the PyPI publishing pipeline.
v2.41.0
v2.41.0 adds moderation support to both the Responses API and Chat Completions API. The change introduces a new optional `moderation` configuration (currently only a `model` field) and extends response/chunk models to carry moderation results when that option is used.
Featuresv2.40.0
v2.40.0 adds support for Amazon Bedrock's OpenAI-compatible “Responses” API by introducing BedrockOpenAI and AsyncBedrockOpenAI clients. It also improves configuration so Bedrock API keys can be set directly on the client/module client. The bulk of the change is new Bedrock-specific client logic plus wiring into the library’s module client selection.
Featuresv2.39.0
v2.39.0 adds new Admin Organization audit log event types for workload identity providers, and introduces support for an additional_tools item in Responses/Conversation parsing. It also updates ActionSearch.query handling to be optional as described in the release notes. The code diff additionally introduces a new request parameter (personality) and updates prompt cache retention documentation, neither of which are mentioned in the release notes.
Featuresv2.38.0
Release v2.38.0 contains a largely automated OpenAPI/Stainless update, reflected by a very large number of generated model/type additions (+9938 lines, -18 lines deleted). The release notes are high-level and do not explicitly list concrete API surface changes, fixes, or breaking behavior.
v2.37.0
v2.37.0 adds a new optional request parameter, `service_tier`, to the Responses `compact` method. It also improves request validation for Pydantic iterators by eagerly validating iterable inputs, and adjusts workload identity auth to stop sending an unnecessary `client_id`.
BreakingFeaturesv2.36.0
v2.36.0 is a Realtime-focused release that expands the SDK surface for a new reasoning-capable model family and a new whisper transcription path. The release notes only mention “manual updates” and “realtime 2”, but the code also introduces new configuration types, new model enum values, and a Realtime session response shape change that is not called out in the notes.
Features