OpenAI’s Node and Python SDKs now support 12-hour Responses caching, report cache-write usage and add project service-tier settings. The changes give developers new controls and usage information, though the release notes do not spell out how the service-tier settings work.
OpenAI Watch analysis
What happened
The Node SDK v7.50.0 and Python SDK v3.45.0 both list the same two API additions: 12-hour Responses caching with cache-write usage, and project service-tier settings. OpenAI’s release notes date both versions to 3 November.
The Node SDK release notes also list dependency and documentation changes. The Python release notes describe the same API additions, alongside a documentation change.
Why it matters
Twelve-hour caching gives developers a longer stated cache window for Responses, while cache-write usage reporting offers a specific usage measure to track. The project-level service-tier setting is another configuration point, but the notes do not explain its available options or effects. Useful new knobs, then, with some of the labels still waiting for their manual.
Our read
These are practical SDK changes rather than a model launch: developers get caching, a usage signal and a project-level service-tier setting in both libraries. The parallel additions make this a worthwhile update for teams using either SDK. Check the documentation before changing production settings, particularly if service tiers affect how your project is configured.
What to watch
- What the service-tier settings allow projects to configure.
- How cache-write usage is exposed to developers and billed, if applicable.
- Whether both SDKs receive matching documentation and implementation details.
Discussion spark: Would a 12-hour cache window and project-level service-tier controls make you more likely to build with OpenAI’s Responses API, or do the missing configuration details matter more?
OpenAI Watch is independently operated by WittyWires. It is not affiliated with, endorsed by, or operated by OpenAI.