Add Cerebras provider support #3486
Open
+255
−117
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 CerebrasProvider using OpenAI SDK for Cerebras's OpenAI-compatible API - Support for Llama 3.3, Qwen 3, GPT-OSS, and GLM models - Add cerebras optional dependency group - Add documentation with usage examples and UTM tracking
- Simplify documentation with single sync example - Fix test to expect None for unknown models - Add missing newline at end of file - All provider and documentation tests now pass
Collaborator
|
@sebastiand-cerebras Hey Seb, Cerebras is already documented at https://ai.pydantic.dev/models/openai/#cerebras as it uses the In #3089, we're implementing a new Would it be an option to do same thing for Cerebras, implementing support for any Cerebras-specific additions to the chat completions API? PS. We have a private Slack channel with Cerebras; happy to discuss this more there as well |
Kludex
reviewed
Nov 20, 2025
- Implement CerebrasModel subclassing OpenAIChatModel - Disable web search (Cerebras-specific feature) - Use cerebras-cloud-sdk for official API support - All tests passing (6/6 Cerebras-specific tests)
Implement CerebrasModel and CerebrasProvider using cerebras-cloud-sdk to provide ultra-fast inference powered by Cerebras Wafer-Scale Engine. Key features: - CerebrasModel extends OpenAIChatModel with web search disabled - Custom _completions_create override to handle SDK compatibility: - Filters OMIT and NOT_GIVEN parameters - Removes unsupported web_search_options parameter - Converts Cerebras SDK response to OpenAI ChatCompletion format - CerebrasProvider uses AsyncCerebras client from cerebras-cloud-sdk - Updated KnownModelName with current Cerebras model list
- Changed CerebrasProvider to use AsyncOpenAI instead of AsyncCerebras SDK - Simplified CerebrasModel by removing custom _completions_create override - Updated dependency from cerebras-cloud-sdk to openai package - Follows OpenRouter pattern for consistency - Reduced codebase by ~200 lines while maintaining all functionality - All Cerebras tests passing (5/5) This aligns with Pydantic team's request to use OpenAI-compatible approach and removes the need for a separate SDK dependency.
- Add test for UserError when no API key provided - Add test for passing openai_client directly - Achieves 100% coverage for cerebras.py
Author
|
Thank you so much for your feedback! I did add these:
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Thank you for reviewing this.