Quota Increase Instantly Denied After Request - Manual Review Requested

Google Cloud Build with AI Custom ML & MLOps
1

I am a software developer working on a personal development project using Claude models via Vertex AI on Google Cloud. Billing is enabled with the 300 USD free trial credit, and I have successfully enabled Claude Sonnet 4.6 and Claude Opus 4.7 in the EU multi-region and europe-west1 via Model Garden. So I also have “pay as you go” enabled.

However, every quota increase request is being instantly and automatically denied within seconds — without any manual review. The quota for all Claude models is stuck at 0. This blocks me completely in two places:

  1. Vertex AI Studio (Google Cloud Console chatbot) — after enabling the model, I immediately receive “Quota has been exhausted” when trying to send any message

  2. Claude Code CLI — returns 429 RESOURCE_EXHAUSTED errors on every request

Affected quotas (all denied instantly):

  • anthropic-claude-sonnet-4-6 — EU multi-region — input/output tokens/min + requests/min

  • anthropic-claude-opus-4-7 — EU multi-region — input tokens/min

  • anthropic-claude-sonnet-4-6 — europe-west1 — output tokens/min

Is that a known problem, and is there a solution?

1 Like