# Claude Code 2.1.322 — fast mode comes to Google Vertex AI

> Claude Code 2.1.322 lets teams on Google Vertex AI use fast mode, with a safe fallback to normal speed.

- Org: Anthropic
- Date: 2026-11-10
- Category: tool
- Source: https://github.com/anthropics/claude-code/releases/tag/v2.1.322
- Canonical page: https://ai-tldr.dev/releases/anthropic-claude-code-2-1-322/

## In short

Claude Code 2.1.322 adds fast mode on Google Vertex AI in the global, us and eu regions. When Vertex refuses a fast request, Claude Code falls back to standard speed instead of failing.

## What it is

Fast mode on Google Vertex AI is the one change in Claude Code 2.1.322. It works in the Vertex global, us and eu regions, so teams that reach Claude through Google Cloud get the faster output mode as well.

## How it works

When a session runs in fast mode on Vertex, Claude Code asks Vertex for fast serving. If Vertex refuses the request, the CLI falls back to standard speed on the same session instead of stopping with an error.

## Why it matters

Companies that buy Claude through Google Cloud no longer have to choose between their Vertex billing setup and the faster output that direct API users get. The fallback means a refused fast request does not break an agent run.

## Who it's for

Claude Code users who run Claude through Google Vertex AI

## Try it

npm i -g @anthropic-ai/claude-code@2.1.322

## Links

- [Release Notes](https://github.com/anthropics/claude-code/releases/tag/v2.1.322)
- [Repository](https://github.com/anthropics/claude-code)