feat(providers): add Groq as new LLM provider #2586
Closed
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 Groq provider types (api.ts, messages.ts, tools.ts, index.ts) - Add Groq to SupportedProviders schema - Add Groq to model-constants with fastest/best model patterns - Add Groq client integration with @ai-sdk/groq - Add Groq config (API key and base URL) Groq is OpenAI-compatible and uses LPU inference for fast responses. Base URL: https://api.groq.com/openai/v1 Relates to archestra-ai#1856
- Add groq to proxied model creators - Add groq to model fetchers with fetchGroqModels function - Add groq to seed data (env vars, display names) - Add groq to optimization rules (prices, rules) - Add groq to error handlers (using OpenAI-compatible parsing) - Add groq to API key fallbacks All TypeScript type checks pass. Relates to archestra-ai#1856
Work in progress - adding Groq provider configs to e2e test suite.
- tool-invocation.spec.ts - tool-persistence.spec.ts - token-cost-limits.spec.ts - model-optimization.spec.ts - tool-result-compression.spec.ts Groq uses OpenAI-compatible API with LPU inference.
Includes: - OpenAI-compatible API details - Base URL and authentication format - Environment variables - Popular models - Getting an API key link
|
|
Collaborator
Author
|
@CLAassistant check |
1 similar comment
Author
|
@CLAassistant check |
Author
|
recheck |
joeyorlando
reviewed
Feb 5, 2026
Contributor
joeyorlando
left a comment
joeyorlando
left a comment
There was a problem hiding this comment.
hi there 👋
Thanks for your contribution. I'm going to close out this PR. It is missing a short demo-video, and the e2e tests will not pass (as there are no wiremock .json response files added for groq).
Please see our Contribution Guidelines, in particular the "Contribute Responsibly" section.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Summary
Adds Groq as a new LLM provider. Groq provides ultra-fast inference using custom LPU hardware with an OpenAI-compatible API.
Changes
Type Definitions
src/types/llm-providers/groq/- Full type definitions (api, messages, tools)Backend Integration
proxiedModelCreators,preferredSourcePrefixes,providerEnvVars,displayNames,pricesByProvider,rulesByProvider,providerParsers,providerMappers,envApiKeyFallbacks,modelFetchersfetchGroqModelsfunctionShared Constants
groqto SupportedProviders enum and discriminatorsE2E Tests
Added Groq configs to all LLM proxy test files:
Documentation
platform-supported-llm-providers.mdAPI Key
Get free API key at console.groq.com/keys
Environment Variables
ARCHESTRA_GROQ_BASE_URLhttps://api.groq.com/openai/v1ARCHESTRA_CHAT_GROQ_API_KEYTesting
pnpm type-check)Notes
Groq uses OpenAI-compatible API, so error handling reuses existing OpenAI parsers/mappers. All integration points follow established patterns.
Closes #1856