NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #97 most downloaded on PyPI
The official Python library for the openai API
Latest stable
3.55.1
Last release today
18 Nov 2026
Ships on a steady schedule
a new release about every 9 days
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
7 years old
476 releases · first in 2020
Drag across the ruler to compare, or tap a release to open it.
docs: document how to do per-request http client customization
docs: minor update to formatting of API link in README
Your coding agent can read these notes before it upgrades. Set up the MCP server →
threads/runs/create_and_run_stream: correct tool_resources param
Full Changelog: v1.35.12...v1.35.13
azure: refresh auth token during retries
internal: minor request options handling changes
## 1.35.10 (2024-07-03) Full Changelog: v1.35.9...v1.35.10 ### Chores * ci: update rye to v0.35.0
client: always respect content-type multipart/form-data if provided
internal: add helper method for constructing BaseModels
build: include more files in sdist builds
## 1.35.6 (2024-06-27) Full Changelog: v1.35.5...v1.35.6 ### Documentation * readme: improve some wording
cli/migrate: avoid reliance on Python 3.12 argument
Full Changelog: v1.35.4...v1.35.5
docs: fix link to advanced python httpx docs
tests: add explicit type annotation
Full Changelog: v1.35.2...v1.35.3
api: add missing parallel_tool_calls arguments
Full Changelog: v1.35.1...v1.35.2
client/async: avoid blocking io call for platform headers
api: add service tier argument for chat completions
## 1.34.0 (2024-06-12) Full Changelog: v1.33.0...v1.34.0 ### Features * api: updates
api: adding chunking_strategy to polling helpers
remove erroneous thread create argument
## 1.32.0 (2024-06-06) Full Changelog: v1.31.2...v1.32.0 ### Features * api: updates
internal: minor refactor of tests
internal: minor change to tests
## 1.31.0 (2024-06-03) Full Changelog: v1.30.5...v1.31.0 ### Features * api: updates (#1461) (0d7cc5e) ### Chores * fix lint
## 1.30.5 (2024-05-29) Full Changelog: v1.30.4...v1.30.5 ### Chores * internal: fix lint issue
add missing __all__ definitions
ci: update rye install location
ci: update rye install location
internal: add slightly better logging to scripts
## 1.30.0 (2024-05-14) Full Changelog: v1.29.0...v1.30.0 ### Features * api: add incomplete state
## 1.29.0 (2024-05-13) Full Changelog: v1.28.2...v1.29.0 ### Features * api: add gpt-4o model
client: accidental blocking sleep in async code
## 1.28.1 (2024-05-11) Full Changelog: v1.28.0...v1.28.1 ### Chores * docs: add SECURITY.md
## 1.28.0 (2024-05-09) Full Changelog: v1.27.0...v1.28.0 ### Features * api: add message image content
## 1.27.0 (2024-05-08) Full Changelog: v1.26.0...v1.27.0 ### Features * api: adding file purposes
api: add usage metadata when streaming
readme: fix misleading timeout example value
## 1.25.1 (2024-05-02) Full Changelog: v1.25.0...v1.25.1 ### Chores * internal: bump prism version
## 1.25.0 (2024-05-01) Full Changelog: v1.24.1...v1.25.0 ### Features * api: delete messages
internal: add link to openapi spec
client: log response headers in debug mode
internal: update test helper function
internal: use actions/checkout@v4 for codeflow
api: change timestamps to unix integers
## 1.23.3 (2024-04-23) Full Changelog: v1.23.2...v1.23.3 ### Chores * internal: restructure imports
api: correct types for message attachment tools
api: correct types for attachments
api: add request id property to response classes
internal: ban usage of lru_cache
internal: add lru_cache helper function
api: docs and response_format response property
## 1.21.0 (2024-04-17) Full Changelog: v1.20.0...v1.21.0 ### Features * api: add vector stores
client: add header OpenAI-Project
errors: add request_id property
## 1.18.0 (2024-04-15) Full Changelog: v1.17.1...v1.18.0 ### Features * api: add batch API (#1316) (3e6f19e) * api: updates
## 1.17.1 (2024-04-12) Full Changelog: v1.17.0...v1.17.1 ### Chores * fix typo (#1304) (1129082) * internal: formatting
api: add additional messages when creating thread run
client: correct logic for line decoding in streaming
internal: defer model build for import latency
api: add support for filtering messages by run_id
revert regression with 3.7 support
One column per quarter.