meta-llama/llama-4-maverick-17b-128e-instruct on Groq
Groq retired meta-llama/llama-4-maverick-17b-128e-instruct on 9 March 2026. Calls to it now fail. Groq recommends openai/gpt-oss-120b. This is Groq's date for its API; the model's maker and other hosts set their own.
| Provider | Groq (hosts other makers' models) |
|---|---|
| Model | meta-llama/llama-4-maverick-17b-128e-instruct by Meta |
| Status | Retired (as of 14 Nov 2026) |
| Shutdown | 9 March 2026 |
| Replacement | openai/gpt-oss-120b |
| Moving to it | Fewer features · gpt-oss reads text only: calls that send images need a different model. |
| Model type | Text |
| Source | Groq: deprecations |
How Driftline finds it
meta-llama/llama-4-maverick-17b-128e-instruct could also mean something else (other services use the same name for their own copy of the model), so Driftline counts it only in files that show they call Groq: groq imports, GROQ_API_KEY or api.groq.com, or a groq/ prefix.
Check your code for it
Run this in your repository. No install and no API key; it lists every OpenAI, Anthropic, Google, Mistral, xAI, Cohere, DeepSeek, Groq, Bedrock, Vertex AI and Azure model ID it finds, with its retirement date and replacement:
npx -y @aidriftline/driftline .
Or look for this ID only: grep -rn "meta-llama/llama-4-maverick-17b-128e-instruct" . (misses aliases, Bedrock and Vertex names, and IDs split across lines).
To be warned automatically before the next retirement, add the free Driftline GitHub Action. It annotates the exact line in pull requests and can fail the build on retired models.
Where a new name is the whole change, Driftline can make it for you: npx -y @aidriftline/driftline fix --dry-run shows the edits, and the Action's fix-pr: true opens one pull request with them, plus a checklist for the lines that need more. See an example pull request.
Read from Groq's official page on 14 November 2026, checked every 6 hours. Something wrong? hello@aidriftline.com