# nvidia/llama-3_1-nemotron-ultra-253b-v1

Calls to the model nvidia/llama-3_1-nemotron-ultra-253b-v1 on Nebius stopped working on August 31, 2026.

On August 31, 2026, Nebius retired model nvidia/llama-3_1-nemotron-ultra-253b-v1. Calls targeting this model fail since that day.

## What to use instead

Move to nvidia/nemotron-3.5-super-vl. The initially named replacement, nvidia/nemotron-3-super-120b-a12b, stops working on November 9, 2026.

- API: Nebius (api.studio.nebius.ai)
- Model: nvidia/llama-3_1-nemotron-ultra-253b-v1
- Kind: Model retirement
- Takes effect: August 31, 2026
- Calls after that day: fail
- Calls it hits: `model nvidia/llama-3_1-nemotron-ultra-253b-v1`
- Source: [Model notices](https://docs.tokenfactory.nebius.com/llms.txt#deprecation)
- Verified: November 6, 2026, against Nebius's own pages
- Page: https://www.okapi.bot/models/nebius/nvidia/llama-3_1-nemotron-ultra-253b-v1/

## Nebius's words

> Deprecating Model: nvidia/Llama-3_1-Nemotron-Ultra-253B-v1; Recommended Replacement: nvidia/nemotron-3-super-120b-a12b

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