feat(models): add latest Groq and Cerebras models

[waleedlatif1]

Summary

• Groq: add qwen/qwen3.6-27b (Preview, $0.60/$3.00 per 1M, 131k context) - confirmed live on console.groq.com/docs/models, was missing from the catalog
• Groq: mark llama-4-scout-17b-16e-instruct and qwen3-32b deprecated - both have an announced shutdown date of July 17, 2026 per Groq's own deprecations page
• Cerebras: add gemma-4-31b (Preview, $0.99/$1.49 per 1M, 131k context / 40k max output) - confirmed live on inference-docs.cerebras.ai, was missing from the catalog

Type of Change

• New feature (model catalog update)

Testing

• Every field independently verified against 2+ live sources (provider docs + pricing pages) before adding, no fabricated data
• No provider code changes needed - confirmed both providers have no per-model special-casing, generic OpenAI-compatible completions
• Full app test suite: 811 files / 11141 tests passing
• bun run lint and bun run type-check clean

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		Jul 10, 2026 4:53pm

[cursor]

PR Summary

Low Risk
Catalog-only metadata in a single file; no runtime provider or auth changes.

Overview
Updates the static provider catalog in models.ts so Groq and Cerebras match current provider offerings.

Cerebras adds cerebras/gemma-4-31b with preview pricing, 131k context, and 40k max output.

Groq adds groq/qwen/qwen3.6-27b and flags groq/qwen/qwen3-32b and groq/meta-llama/llama-4-scout-17b-16e-instruct as deprecated ahead of Groq’s shutdown timeline. Existing workflows can keep using those IDs; pickers and copilot metadata can surface the deprecation flag.

No inference or routing code changes—only catalog metadata for pricing, capabilities, and UI.

^{Reviewed by Cursor Bugbot for commit 12f19c4. Configure here.}

[greptile-apps]

Greptile Summary

This PR updates the model catalog for Groq and Cerebras. The main changes are:

• Added cerebras/gemma-4-31b with pricing, limits, and release date metadata.
• Added groq/qwen/qwen3.6-27b with pricing, limits, and release date metadata.
• Marked two older Groq models as deprecated.

Confidence Score: 5/5

This looks safe to merge.

• No blocking issues found in the changed code.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Updates static model definitions for Groq and Cerebras, including release dates used by catalog ordering.

_{Reviews (2): Last reviewed commit: "fix(models): add verified releaseDate fo..." | Re-trigger Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit 12f19c4. Configure here.}