# grok-4-fast-non-reasoning

Since May 15, 2026, xAI answers calls to the model grok-4-fast-non-reasoning from a newer version.

On May 15, 2026, the model grok-4-fast-non-reasoning was retired. Calls using model grok-4-fast-non-reasoning are redirected to grok-4.3 with none reasoning effort rather than failing.

## What to use instead

Update your requests to use grok-4.3 with none reasoning effort, as recommended by xAI.

- API: xAI (api.x.ai)
- Model: grok-4-fast-non-reasoning
- Released: December 18, 2025 (models.dev)
- Kind: Model retirement
- Takes effect: May 15, 2026
- Calls after that day: answered by a newer version
- Calls it hits: `model grok-4-fast-non-reasoning`
- Source: [Model notices](https://docs.x.ai/llms.txt#model-retirement)
- Verified: November 6, 2026, against xAI's own pages
- Page: https://www.okapi.bot/models/xai/grok-4-fast-non-reasoning/

## xAI's words

> Model being retired: grok-4-fast-non-reasoning; Redirect target after May 15: grok-4.3 with none reasoning effort

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