Add grok-4 and groq kimi-k2 models #2235
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- Add grok:grok-4 as a known model name - Add grok-4 plain model name support (provider inference) - Add groq:moonshotai/kimi-k2-instruct to Groq preview models - Add test cases for grok model variants - Update CLI test to include grok provider
|
@DouweM the groq/grok changes are ready to review |
DouweM
requested changes
Jul 17, 2025
DouweM
requested changes
Jul 17, 2025
zachmayer
commented
Jul 17, 2025
|
Would it make sense to make this PR just for the grok models? and then move the |
|
Ok I think I responded to all the feedback here. Let me know how things look or if I need other changes. |
DouweM
changed the title
|
@zachmayer Thanks Zach! |
|
Awesome thank you! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Extracted from #2211 for easier review.
Closes #2187
This PR adds support for new Grok and Groq models:
Both grok and groq models use existing OpenAI-compatible infrastructure, so this is primarily adding model names and test coverage.