openai/openai-python
Read the upstream summary on the left, browse the cached forks below it, and load each fork comparison into the right-hand panel.
openai/openai-python
openai/openai-python is the official Python client for the OpenAI API. It targets Python 3.9+, provides typed sync and async clients over httpx, is generated from OpenAPI with Stainless, and is actively maintained with frequent releases and recent commits.
Jump straight into Discofork's strongest cached fork picks, or open a compare view in one click.
Choose a fork to inspect
Prefer upstream unless you specifically need this exact snapshot. This fork does not show added capabilities, and its main tradeoff is lag behind current upstream fixes.
Prefer upstream unless you specifically need this fork's older, customized behavior. The fork looks materially stale and significantly diverged, so it is better suited as a legacy or product-specific SDK than as a general-purpose dependency.
Choose this fork only if you intentionally want an older, frozen OpenAI client and can accept substantial drift from upstream. For new work or active maintenance, upstream is the better choice.
Prefer this fork only if the added function-calling docs are the main value and you can tolerate being far behind upstream. If you need current SDK behavior, types, or API coverage, upstream is the safer choice.
Choose this fork only if you want a customized OpenAI Python client and are prepared to own divergence. Prefer upstream if you need broad API coverage, current fixes, and low maintenance risk.
Prefer upstream unless you need a frozen baseline to customize yourself. This fork adds no visible features and is materially behind the official SDK, so it is a weak choice for adopters who want current API coverage or ongoing maintenance.
Prefer the upstream `openai-python` unless you specifically need this fork's legacy behaviors or compatibility hacks. This fork looks useful as a transitional/maintenance branch for older code, but it is too stale and diverged to be a good default for new adoption.
Prefer upstream unless you specifically need an old frozen client state. This fork shows no added capability and is materially behind current upstream, so it is mainly useful as a stable snapshot, not as a better-maintained or more capable SDK.
Prefer this fork only if you need its specific older/customized behavior and are willing to own long-term maintenance. For most adopters, upstream is the better choice because this fork is stale, materially divergent, and likely missing newer SDK surface and fixes.