# nvidia/nvidia-nemotron-nano-9b-v2

Calls to the model nvidia/nvidia-nemotron-nano-9b-v2 on Together AI stopped working on February 25, 2026.

## What to use instead

Move to Qwen/Qwen3.5-9B, recommended by Together AI.

- API: Together AI (api.together.xyz)
- Model: nvidia/nvidia-nemotron-nano-9b-v2
- Kind: Model retirement
- Takes effect: February 25, 2026
- Calls after that day: fail
- Calls it hits: `model nvidia/nvidia-nemotron-nano-9b-v2`
- Source: [Deprecations page](https://docs.together.ai/docs/deprecations)
- Verified: November 6, 2026, against Together AI's own pages
- Page: https://www.okapi.bot/models/together-ai/nvidia/nvidia-nemotron-nano-9b-v2/

## Together AI's words

> Removal date: 2026-02-25; Model: nvidia/Nvidia-Nemotron-Nano-9B-v2; Supported by on-demand dedicated endpoints: No

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