# qwen/qwen3-32b

Calls to the model qwen/qwen3-32b on Groq stopped working on July 17, 2026.

On July 17, 2026, the model qwen/qwen3-32b was retired. This change affects calls using model qwen/qwen3-32b on free and developer tiers. Requests sent to this model fail since that date.

## The error Groq returns once qwen/qwen3-32b is gone

HTTP 404

```json
{"error":{"message":"The model `qwen/qwen3-32b` 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-120b, which is recommended by Groq.

- API: Groq (api.groq.com)
- Model: qwen/qwen3-32b
- Released: April 2025 (models.dev)
- Kind: Model retirement
- Takes effect: July 17, 2026
- Calls after that day: fail
- Calls it hits: `model qwen/qwen3-32b`
- Who it affects: free and developer tiers
- 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/qwen/qwen3-32b/

## Groq's words

> Deprecated Model: qwen/qwen3-32b; Shutdown Date: 07/17/26; Recommended Replacement Model ID: openai/gpt-oss-120b

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