Grok API changelog

Grok API adds custom moderation controls for text requests on October 27

A guidelines array on Chat Completions or Responses API requests sets how Grok handles the nsfw, violence and profanity categories. Grok follows the guidelines as it writes its response.

Who is affected:

Developers who call Grok text endpoints and need to control content handling.

What to do:

Add a guidelines array to your requests if you want to set content handling per category.

xAI retires older Grok models, requests redirect to Grok 4.3

On May 15, 2026 xAI retired grok-4-1-fast, grok-4-fast, grok-4-0709, grok-code-fast-1, grok-3 and grok-imagine-image-pro. Requests to these slugs redirect to grok-4.3 (or grok-build-0.1 for grok-code-fast-1) and are billed at grok-4.3 rates of $1.25 input and $2.50 output per 1M tokens.

Who is affected:

Apps still calling the retired Grok slugs, which now get a different model at a different price.

Action needed:

Set the model explicitly to grok-4.3 with the reasoning effort you want, or grok-build-0.1 for coding.