# nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 — Removed — shutdown August 31, 2026

For nvidia/Llama-3_1-Nemotron-Ultra-253B-v1, provider is Nebius Token Factory; lifecycle status is Removed; shutdown / retirement date is August 31, 2026; recommended replacement is nvidia/nemotron-3-super-120b-a12b; platform / deployment scope is Nebius Token Factory serverless (dedicated endpoints unaffected), recorded from its source on 2026-09-16.

- **Provider:** Nebius Token Factory _(our reading, not quoted from the source)_
- **Model ID / API name:** nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 _(verified: appears in the quote below)_
- **Lifecycle status:** Removed
- **Shutdown / retirement date:** August 31, 2026 _(verified: appears in its own passage below)_
- **Recommended replacement:** nvidia/nemotron-3-super-120b-a12b _(verified: appears in the quote below)_
- **Platform / deployment scope:** Nebius Token Factory serverless (dedicated endpoints unaffected) _(our reading, not quoted from the source)_

## What the source says

> | [`nvidia/Llama-3_1-Nemotron-Ultra-253B-v1`](https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2FLlama-3_1-Nemotron-Ultra-253B-v1) | [`nvidia/nemotron-3-super-120b-a12b`](https://tokenfactory.nebius.com/models/catalog/text2text/nvidia%2Fnemotron-3-super-120b-a12b)           |

## Where each value comes from

This source states these in separate places, so each value is shown with the passage that states it.

### Shutdown / retirement date

> These models will be removed from Token Factory on **August 31, 2026**.

### Platform / deployment scope

> Affected Serverless models will no longer be available via API or Playground.

## Source

- https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice.md
- https://docs.tokenfactory.nebius.com/august-2026-deprecation-notice

Last verified: 2026-09-16. Review by: 2026-10-16.
Part of [AI model deprecation and retirement dates by provider](https://referencesource.org/ai-model-deprecation-and-retirement/).