# cognitivecomputations/dolphin-2.9.1-llama-3-70b

Calls to the model cognitivecomputations/dolphin-2.9.1-llama-3-70b on DeepInfra stopped working on October 10, 2024.

On October 10, 2024, DeepInfra retired model cognitivecomputations/dolphin-2.9.1-llama-3-70b. Calls requesting this model now fail.

## What to use instead

Move to Qwen/Qwen2.5-72B-Instruct, recommended by DeepInfra.

- API: DeepInfra (api.deepinfra.com)
- Model: cognitivecomputations/dolphin-2.9.1-llama-3-70b
- Kind: Model retirement
- Takes effect: October 10, 2024
- Calls after that day: fail
- Calls it hits: `model cognitivecomputations/dolphin-2.9.1-llama-3-70b`
- 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/cognitivecomputations/dolphin-2.9.1-llama-3-70b/

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