# qwen/qwen3-32b

Calls to the model qwen/qwen3-32b on Nebius stopped working on August 31, 2026.

On August 31, 2026, Nebius will retire the qwen/qwen3-32b model. Calls targeting model qwen/qwen3-32b after this date will fail. Update your integrations before this shutdown to avoid disruptions.

## What to use instead

Move to nvidia/Nemotron-3_5-Lightning, which is recommended by Nebius.

- API: Nebius (api.studio.nebius.ai)
- Model: qwen/qwen3-32b
- Kind: Model retirement
- Takes effect: August 31, 2026
- Calls after that day: fail
- Calls it hits: `model qwen/qwen3-32b`
- Source: [Model notices](https://docs.tokenfactory.nebius.com/llms.txt#deprecation)
- Verified: October 26, 2026, against Nebius's own pages
- Page: https://www.okapi.bot/models/nebius/qwen/qwen3-32b/

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