/v1/fine_tuning/jobs (new job creation)
OpenAI retires /v1/fine_tuning/jobs (new job creation) on 6 January 2027 (in 51 days).
| Provider | OpenAI |
|---|---|
| Status | retiring |
| Shutdown date | |
| Deprecated on | |
| Replacement | none named |
| Source | https://developers.openai.com/api/docs/deprecations#update-to-openais-self-serve-fine-tuning |
| Note | system: self-serve fine-tuning. 2026-05-07: no FT for orgs that never ran FT; 2026-07-02: no new jobs for orgs without FT inference in past 60 days; 2027-01-06: active existing customers can no longer create new FT jobs. Inference on fine-tuned models continues until the base model is deprecated |
Before 6 January 2027: move off it safely
- Find every call to it in your code (Python, JS/TS, Go, Java, configs, notebooks), with nothing to install:
uvx llmshift scan
Then llmshift init --github keeps the check on every pull request. LLMShift is free and open source (MIT) and runs on your machine.
Other OpenAI retirements
agent builder: retires 2026-11-30chatgpt-image-latest: retires 2026-12-01gpt-image-1-mini: retires 2026-12-01gpt-image-1.5: retires 2026-12-01gpt-image-1.5-2025-12-16: retires 2026-12-01gpt-5: retires 2026-12-11
Wrong date or replacement? Tell us on GitHub, with a link to the provider's page.
Lifecycle data updated 2026-11-14, collected from the providers' official deprecation pages. Dates can move: check the source before you plan around one. Visits are counted with GoatCounter, which sets no cookies.