# nvidia/llama-3.1-nemotron-70b-instruct

Calls to the model nvidia/llama-3.1-nemotron-70b-instruct on DeepInfra stopped working on July 16, 2026.

DeepInfra retired the model nvidia/llama-3.1-nemotron-70b-instruct on July 16, 2026. Calls specifying this model fail since that date.

## What to use instead

Move to nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, which is recommended by DeepInfra.

- API: DeepInfra (api.deepinfra.com)
- Model: nvidia/llama-3.1-nemotron-70b-instruct
- Released: April 15, 2025 (models.dev)
- Kind: Model retirement
- Takes effect: July 16, 2026
- Calls after that day: fail
- Calls it hits: `model nvidia/llama-3.1-nemotron-70b-instruct`
- Source: [Model list](https://api.deepinfra.com/models/list)
- Verified: November 6, 2026, against DeepInfra's own pages
- Page: https://www.okapi.bot/models/deepinfra/nvidia/llama-3.1-nemotron-70b-instruct/

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