# gemma2-9b-it

Calls to the model gemma2-9b-it on Groq stopped working on October 8, 2025.

## The error Groq returns once gemma2-9b-it is gone

HTTP 404

```json
{"error":{"message":"The model `gemma2-9b-it` does not exist or you do not have access to it.","type":"invalid_request_error","code":"model_not_found"}}
```

## What to use instead

Move to openai/gpt-oss-20b. llama-3.1-8b-instant, named first, stopped working on 2026-08-16.

- API: Groq (api.groq.com)
- Model: gemma2-9b-it
- Released: June 25, 2024 (models.dev)
- Kind: Model retirement
- Takes effect: October 8, 2025
- Calls after that day: fail
- Calls it hits: `model gemma2-9b-it`
- Source: [Deprecations page](https://console.groq.com/docs/deprecations)
- Verified: November 6, 2026, against Groq's own pages
- Page: https://www.okapi.bot/models/groq/gemma2-9b-it/

## Groq's words

> Deprecated Model: gemma2-9b-it; Shutdown Date: 10/08/25; Recommended Replacement Model ID: llama-3.1-8b-instant

Okapi finds the calls this change hits in your repo and opens the pull request with the fix: https://github.com/apps/okapi-agent