# Claude Code 2.1.322 adds fast mode on Vertex AI in global, US and EU regions

> Anthropic's Claude Code 2.1.322 changelog adds fast mode on Google Vertex AI in the global, US and EU regions, with a fallback to standard speed if Vertex refuses it.

- Status: official (From the company, authors or authority themselves, with a link to their own page.)
- Topic: Products
- Published: 2026-11-10T00:00:00+00:00
- Updated: 2026-11-10T04:08:47.554751+00:00
- Web page: https://ai-news.ikangai.com/story/claude-code-2-1-322-adds-fast-mode-on-vertex-ai-in-global-us-and-eu-regions/
- Seen in: Claude Code changelog
- Change: capability (New capability)
- Takes effect: 2026-11-10
- Applies to: Claude Code, Google Vertex AI, global, US, EU

## What changed

Claude Code 2.1.322 adds fast mode on Google Vertex AI in the global, US and EU regions, falling back to standard speed if Vertex refuses a request.

Anthropic's Claude Code 2.1.322, dated November 10, 2026, adds fast mode on Google Vertex AI in the global, US and EU regions. The changelog entry includes a condition: if Vertex refuses fast mode for a request, Claude Code drops to standard speed instead of failing. It is one line in the release notes and the only change listed for that version.

The changelog does not explain what fast mode is or how it is served, so readers have to work from the entry alone. The routing is clear enough, though. The feature is offered on Google Vertex AI in three regions, and when Vertex declines a request for fast serving, it falls back to standard speed rather than returning an error. A user who enables fast mode does not end up with a failed request.

The entry for version 2.1.321 contains a related fix. It says fast mode had been losing replies, switching models or retrying for minutes when fast serving was rate-limited, overloaded or failing. Now it tries standard speed on the same model first, so the model stays fixed while only the speed tier drops. The 2.1.321 entry also changed the fast mode labels in /fast, /config and /model to name the current model when it supports fast mode.

The linked pages do not say which Vertex models support fast mode, what the speed difference is, or whether the regional coverage applies to every Claude model on the platform. Readers who want to know whether this affects their deployments will need to check those details elsewhere.

## Why it matters

Teams that run Claude Code through Google Cloud Vertex AI can use fast mode in three regional settings, so response speed now depends on where they deploy.

## What you can do

If you run Claude Code on Vertex AI, check whether your region is covered and plan for standard-speed responses in latency-sensitive workflows.

## Original source

- [Claude Code changelog - Claude Code Docs](https://code.claude.com/docs/en/changelog)
- [claude-code/CHANGELOG.md at main · anthropics/claude-code · GitHub](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md)

---

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it.

Cite as: IKANGAI AI News, "Claude Code 2.1.322 adds fast mode on Vertex AI in global, US and EU regions", 2026-11-10, https://ai-news.ikangai.com/story/claude-code-2-1-322-adds-fast-mode-on-vertex-ai-in-global-us-and-eu-regions/
