whichdevtool?
Menu
StacksDirectory Pricing changes Glossary
VPS and cloud servers App hosting and PaaS Managed databases Transactional email APIs Email marketing and newsletters Domain registrars CDN, DNS and edge security Monitoring, uptime and error tracking Auth and identity Frontend and full-stack frameworks Backend frameworks UI component libraries AI model APIs File and object storage Payments and billing Background jobs, queues and workflows ORMs and database toolkits

Cloud AI model platform · by Google Cloud

Vertex AI (Gemini Enterprise Agent Platform)

Google Cloud's enterprise model platform, now branded Agent Platform, serving Gemini plus partner models such as Claude on a Google Cloud bill.

Visit cloud.google.com ↗ Alternatives Paid EU region
Vertex AI (Gemini Enterprise Agent Platform) homepage
§1

Overview

Vertex AI is Google Cloud's managed AI platform; its generative AI pricing page is now titled Agent Platform, matching the 'Gemini Enterprise Agent Platform' name Google uses for its enterprise tier. It serves the Gemini family (Flash, Flash-Lite, Pro, image and speech models) and partner models such as Anthropic's Claude, all billed to a Google Cloud account.

Gemini prices mirror the Gemini Developer API for global endpoints: Gemini 3.8 Flash is $0.75 in and $3.75 out per million tokens until 31 December 2026, then $1.50 / $7.50. Non-global endpoints add 10%, Priority costs about 1.8x, and Flex and Batch have their own discounted rates. Only successful (HTTP 200) requests are billed.

Unlike the Gemini Developer API, there is no free model tier here. What you get instead is Google Cloud's enterprise machinery: committed-use Flexible Savings Plans, provisioned throughput, regional and multi-region endpoints, and one bill with the rest of your Google Cloud usage.

§2

Pricing and plans

Plan Price What you get
Gemini 3.8 Flash (global) $0.75 in / $3.75 out per 1M Through 2026-12-31; $1.50 / $7.50 from 2027-01-01; non-global +10%
Gemini 3.5 Flash-Lite (global) $0.30 in / $2.50 out per 1M Cached input $0.03
Gemini 3.1 Flash-Lite (global) $0.25 in / $1.50 out per 1M Text, image and video input
Gemini 3.1 Pro Preview (global) $2 in / $12 out per 1M Up to 200K input tokens; $4 / $18 above
Priority About 1.8x e.g. Gemini 3.1 Pro Preview $3.60 / $21.60
Flex / Batch Discounted Separate price tab on the pricing page
Claude on Google Cloud Google-set prices Regional and multi-region endpoints 10% above global, per Anthropic

Per 1M tokens in USD, read 2026-09-29 on cloud.google.com/vertex-ai/generative-ai/pricing (titled 'Agent Platform Pricing'). Only requests returning HTTP 200 are charged. Non-global endpoints cost 10% more than global for current Gemini models. Promotional Flash pricing is delivered as 50% credits back on net spend for a period. Flexible Savings Plans (spend-based committed use discounts) apply to eligible usage. Google Cloud new-customer credits were not confirmed on the pages read. EU region availability was not confirmed in the pages read, so euRegion is left false.

Source: cloud.google.com/vertex-ai/generative-ai/pricing · prices as published, excluding tax.

§3

What it does

Gemini and partner models
Gemini family plus partner models including Anthropic's Claude.
Endpoint types
Global, multi-region and regional endpoints; non-global Gemini pricing is 10% higher.
Priority and Flex/Batch
Pay more for priority capacity or less for flexible and batch processing.
Only successful requests billed
Requests returning 4xx or 5xx codes are not charged.
Flexible Savings Plans
Spend-based committed use discounts across eligible Google Cloud products.
§4

Strengths and limitations

Strengths

  • Gemini and Claude on one Google Cloud bill and contract.
  • Failed requests are not billed.
  • Committed-use discounts through Flexible Savings Plans.

Limitations

  • No free model tier, unlike the Gemini Developer API.
  • Introductory Flash prices double on 2027-01-01.
  • Non-global endpoints cost 10% more.
  • The pricing page is long and split across tiers, regions and context lengths.
§5

Who it suits

Good for

  • Companies already on Google Cloud
  • Teams that want Gemini and Claude under one cloud contract
  • Workloads needing committed-use discounts or provisioned capacity

Look elsewhere if

  • Hobby projects (the Gemini Developer API has a free tier)
  • Teams without a Google Cloud account
§6

Alternatives to Vertex AI (Gemini Enterprise Agent Platform)

Tool From Free option Stages
Mistral API (Mistral Studio) AI model API (model maker)
Usage-based Free tier
Amazon Bedrock Cloud AI model platform
— Paid
OpenAI API AI model API (model maker)
Usage-based Paid
Claude API AI model API (model maker)
Usage-based Trial
Baseten Inference platform (Model APIs and dedicated deployments)
Usage-based Trial
OpenRouter Model router (unified API)
— Free tier

All AI model APIs →

§7

Questions

What is the difference between Vertex AI and the Gemini API?

The Gemini Developer API is Google's developer API with a free tier; Vertex AI (Agent Platform) is the Google Cloud service with regional endpoints, partner models and enterprise billing but no free tier.

How much does Gemini 3.8 Flash cost on Vertex AI?

On a global endpoint, $0.75 per 1M input tokens and $3.75 per 1M output tokens through 31 December 2026, then $1.50 and $7.50; non-global endpoints add 10%.

Can I use Claude on Vertex AI?

Yes. Anthropic's Claude models are available on Google Cloud, priced by Google; regional and multi-region endpoints cost 10% more than global.

Sources read for this page