Cloud AI platform (hyperscaler)

Google Cloud Vertex AI

Vertex AI is Google Cloud's platform for building with Gemini and other hosted models, billed through a Google Cloud account.

Checked 2026-11-05

Vertex AI is Google Cloud's platform for building with Gemini and other hosted models, billed through a Google Cloud account. We cannot give you prices. When we opened Google's pricing page on 5 November 2026 our fetch returned only the page title, which now reads Agent Platform Pricing, so we list no figures and you should read that page directly. The data side we could confirm. Google's data governance page says it will not use your data to train or fine-tune models without your prior permission or instruction. Implicit caching keeps data briefly, and durable cache data is deleted within 24 hours. Customer-managed encryption keys are not supported for durable caching. The global endpoint can serve requests and cached data from any region, so a team with residency rules should pick a regional or multi-regional endpoint. Google may log prompts to detect abuse, and it says zero data retention may not be possible with some advanced AI features. To avoid retention, leave request-response logging off and set store to false in the Interactions API, where it defaults to true. This is a read of published pages, not a test by us. Facts come from Google's data governance page we checked on 5 November 2026.

Mentioned here

Questions

How much does Google Cloud Vertex AI cost?

Models are priced per million tokens, by model, with separate cached-input prices and Priority, Flex or Batch and Provisioned Throughput options. Inputs over 200K tokens are charged at long-context rates, and grounding queries past the free limits are $14 per 1,000 (checked 10 November 2026).

Is Google Cloud Vertex AI OpenAI compatible?

Yes, it offers an OpenAI-compatible API, so most agents and SDKs can point at it by changing the base URL.

Reviews

Loading reviews…

Write a review

Your rating

Up to 1000 characters. Stars alone are enough.

Similar

  • Microsoft Azure AI Foundry

    Microsoft Foundry is Azure's platform for deploying models, including OpenAI models sold by Azure, and for building agents on them.

    • Cloud AI platform (hyperscaler)
    • OpenAI compatible