the diff / Kiro / November 11, 2026

Kiro adds Grok 4.7 at 2.7x credits, experimental

score credits past 200K tokens: 5.4x

Kiro adds Grok 4.7 with experimental support in the IDE, CLI, Crew and Web. 500K context, 2.7x credits up to 200K tokens, 5.4x over.

What changed

Kiro's changelog, dated November 10, adds Grok 4.7 with experimental support in the Kiro IDE, CLI, Crew and Web for Pro, Pro+, Pro Max and Power customers. The context window is 500K tokens. Requests up to 200K tokens are billed at a 2.7x credit multiplier; requests over 200K tokens, 5.4x. To see it in the model list, restart the IDE or CLI, run kirocrew restart for Crew, or refresh Kiro Web.

Why it matters if you ship with an agent

Credits past 200K tokens: 5.4x. The multiplier doubles at the line, and a long agent session crosses it without announcing itself. If you try it, watch the context size and compact before 200K. It is labelled experimental, so do not make it a team default yet.

By MK · Source: https://kiro.dev/changelog/models/grok-4-7-now-available-in-kiro/

more Kiro changes: Kiro previews Enterprise Management: one policy, every client · Kiro IDE 1.4.154 adds Approve for me and renames Autopilot · Kiro CLI 3.0 defaults to V3, retires Classic and the desktop app · Kiro CLI 2.37.0 rewrites V2 agents to V3 by default at launch · Kiro CLI 2.36.0 adds Approve for me, a model that answers the prompt · all

keep handy: AI coding tool pricing tracker · vibe coding vs AI coding · agent fail hall of fame


The Diff is Accept All's short note on changes that alter how you ship with an agent. Older: Kiro previews Enterprise Management: one policy, every client.