xAI
grok-4-fast-reasoning model retirement
RedirectedSubscribe to xAIShare
Calls to model grok-4-fast-reasoning are redirected starting May 15, 2026. After that date, xAI answers these requests using grok-4.3 with low reasoning effort instead of the original model.
What to use instead of grok-4-fast-reasoning
Move to grok-4.3 with low reasoning effort as recommended by xAI.
In xAI's words
Model being retired: grok-4-fast-reasoning; Redirect target after May 15: grok-4.3 with low reasoning effort
Facts
- API
- xAI
api.x.ai - Model
grok-4-fast-reasoning- Released
- December 18, 2025 (models.dev)
- Kind
- Model retirement
- Takes effect
- May 15, 2026
- Calls after that day
- Answered by a newer version
- Source
- Model notices
- Last updated
- Verified
- , against xAI's own pages
Questions
When does this change take effect?
Since May 15, 2026, xAI answers calls to the model grok-4-fast-reasoning from a newer version.
What happens to calls after May 15, 2026?
xAI answers them from a newer version. The response can differ from what your code expects.
When was grok-4-fast-reasoning released?
grok-4-fast-reasoning was released on December 18, 2025, according to models.dev.
How do I find the calls this hits in my code?
Okapi reads your repository, finds the calls this change hits and opens a pull request with the fix. It never commits to your branches: every change comes as a pull request you review.
grok-4-fast-reasoning on other APIs 1
-
Azure AI Foundry
grok-4-fast-reasoningModel retirement Stopped working
More from xAI 10
-
grok-3Model retirement Redirected -
grok-4Model retirement Stopped working -
grok-4-0709Model retirement Redirected -
grok-4-1-fast-non-reasoningModel retirement Redirected -
grok-4-1-fast-reasoningModel retirement Redirected -
grok-4-fast-non-reasoningModel retirement Redirected -
grok-4-latestModel retirement Stopped working -
grok-code-fast-1Model retirement Redirected -
grok-imagine-image-proModel retirement Redirected -
grok-2Model retirement Stopped working
You fixed this one by hand.
Okapi opens the pull request with the fix before the next breaking change reaches your code.