Is there a /v1/responses endpoint?
No. A POST to /v1/responses returns 404. Use /v1/chat/completions.
What we found
The newer Responses API is not implemented here, and a POST to that path returns a 404 rather than an error that could be mistaken for a model problem. The surface we serve is chat completions, plus the models listing.
In practice this affects a small number of SDK code paths that prefer the newer endpoint when they detect it. Because the 404 is clean, those SDKs fall back rather than fail. A client pinned to the Responses API will not work here.
How this was measured
An unattributed measurement is a marketing claim, so here is the receipt.
- Probe
- probe_litellm.py
- Measured
- 2026-09-08
- Applies to
- every model we serve
We found this by running the probe against the models we serve, which is also why it is worth trusting: it is a reading rather than a restatement of somebody's documentation. The full catalog is on /models, and what a request costs is on /pricing.
Upstream behaviour changes without notice, and a measurement is only as good as its date. If you find this is no longer true, tell us on the support page and we will re-run the probe.