Commit graph

4 commits

Author SHA1 Message Date
Oleksiy Syvokon
2a57b160b0
openai: Don't send prompt_cache_key for OpenAI-compatible models (#36231)
Some APIs fail when they get this parameter

Closes #36215

Release Notes:

- Fixed OpenAI-compatible providers that don't support prompt caching
and/or reasoning
2025-08-15 13:54:24 +03:00
Bennet Bo Fenner
59aeede50d
vercel: Use proper model identifiers and add image support (#33377)
Follow up to previous PRs:
- Return `true` in `supports_images` - v0 supports images already
- Rename model id to match the exact version of the model `v0-1.5-md`
(For now we do not expose `sm`/`lg` variants since they seem not to be
available via the API)
- Provide autocompletion in settings for using `vercel` as a `provider`

Release Notes:

- N/A
2025-06-25 13:26:41 +00:00
Bennet Bo Fenner
18f1221a44
vercel: Reuse existing OpenAI code (#33362)
Follow up to #33292

Since Vercel's API is OpenAI compatible, we can reuse a bunch of code.

Release Notes:

- N/A
2025-06-25 15:04:43 +02:00
Danilo Leal
94735aef69
Add support for Vercel as a language model provider (#33292)
Vercel v0 is an OpenAI-compatible model, so this is mostly a dupe of the
OpenAI provider files with some adaptations for v0, including going
ahead and using the custom endpoint for the API URL field.

Release Notes:

- Added support for Vercel as a language model provider.
2025-06-24 11:02:06 -03:00