Claude Code 2.1.322 adds fast mode on Google Vertex, with a quiet fallback to standard speed

Claude Code 2.1.322, released 10 November 2026, adds fast mode on Vertex in the global, US and EU regions. If Vertex refuses it, Claude Code falls back to standard speed.

The Claude Code changelog lists version 2.1.322, dated 10 November 2026, with one change: fast mode is now available on Vertex in the global, us and eu regions. If Vertex refuses fast mode, Claude Code falls back to standard speed.

What changed

Teams that run Claude Code through Google Cloud’s Vertex AI, usually because procurement, billing or data-residency rules keep AI traffic inside an existing cloud contract, can now use the faster output option that was previously tied to other routes. The region options include an EU one.

The detail worth reading twice

The fallback is automatic. If Vertex declines a fast request, the session carries on at standard speed. The changelog does not say the user is warned, so a developer may be waiting longer without knowing why. It does not state any pricing for fast mode on Vertex either, so treat cost as something to confirm with your cloud account, not assume.

What it means

The news is less about speed than about where AI coding tools can run. Each release that adds a cloud route makes it easier for a regulated or enterprise buyer to approve AI-assisted development inside infrastructure they already govern. That removes a common objection from security reviews.

So what

If you are commissioning software and want AI-assisted delivery, ask which cloud route the tooling uses, which region, and what happens to your code there. Our AI-assisted development service is built around those answers being explicit, and healthcare software development adds the data-handling rules that sector needs. When you are ready, start a project.

← All research

More research.

GitHub's Copilot metrics now flag developers whose usage data is missing

GitHub's 5 November 2026 changelog adds fields to the Copilot usage metrics API showing which users send no telemetry or run outdated editors. AI coding tool reporting now admits its own blind spots.

Read ›

Claude Code 2.1.323 adds experimental Code Mode and plugin version ranges

Claude Code 2.1.323 adds an opt-in Code Mode where Claude writes JavaScript to call its tools, and lets plugins declare which Claude Code versions they support. Claude Code teams get more control over extensions.

Read ›

GitHub Apps can now manage enterprise Copilot seats through the API

GitHub's 10 November 2026 changelog lets enterprise GitHub Apps assign and remove Copilot seats through a new permission. Seat management for AI coding tools can now be automated.

Read ›

GitHub will switch off Dependabot alerts on year-old inactive repositories from 8 December

From 8 December 2026, GitHub will turn off Dependabot alerts on most repositories with no activity in the past year. If you own software that is stable but unmaintained, your security alerts go quiet.

Read ›

Gemini 4 Carbon arrives in GitHub Copilot, and it can switch itself on for your whole organisation

GitHub made Gemini 4 Carbon generally available in Copilot on 10 November 2026 across ten clients. Under default model enablement, Business and Enterprise organisations get new models automatically unless an admin opts out.

Read ›

Claude Fable 5.2 in GitHub Copilot: off by default for Business and Enterprise, with data retention you must accept

GitHub made Claude Fable 5.2 generally available in Copilot on 9 November 2026 across ten clients including Xcode, JetBrains and Copilot CLI. Business and Enterprise admins must switch on a policy that is off by default and accepts Anthropic's data retention.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work