03 Anthropic InfraDev tools

Claude Models on Google Cloud (Anthropic managed) is GA: the full Claude Platform on your Google Cloud commitment

The full Claude Platform, available on Google Cloud
Image: Anthropic Concept illustration (generated)

What is it?

Claude Models on Google Cloud (Anthropic managed) lets you call the Anthropic-operated Claude API directly from a Google Cloud project. Authentication uses Google Cloud IAM roles such as roles/claude.user instead of API keys, and usage is billed on your Google Cloud Marketplace invoice and draws down existing Google Cloud commitments. Features like Managed Agents (beta), code execution, Agent Skills, the Files API, and prompt caching arrive the same day they do on the native Claude Platform; in Python you use the AnthropicGoogleCloud client.

pip install -U "anthropic[google_cloud]"

Why does it matter?

Until now, running Claude on Google Cloud meant the Google-operated Vertex offering, where new features often showed up late. Now teams can keep their Google Cloud commitments and IAM setup and still get the latest betas right away. Fast mode for Opus 5.5 is also GA here, with up to 2.5x faster outputVendor claim at $8 per million input tokens and $40 per million output tokens. Anthropic, not Google, is the data processor, though, so if you have strict data residency requirements or need Model Armor, stay on the Google-managed offering.

Maturity

GAGenerally available. Only US and Global endpoints are offered, and the dedicated SDK client is still in beta.

How to track it

  • Wider rollout: watch the setup docs for regional endpoints beyond US and Global.
  • SDK: check the Claude Platform release notes for the AnthropicGoogleCloud client leaving beta.
  • Feature gaps: follow the Feature support section of the docs to see whether the unsupported list (MCP tunnels and others) shrinks.

More from the same day