Independent reference. We are independent of every vendor listed. No affiliate links. No sponsored placements.
Hyperscaler agent platform

Google Vertex AI Agent Builder

Cheapest published
Gemini 3.5 Flash input, $1.50 per 1M tokens

Where Google Vertex AI Agent Builder sits in the cluster

Cheapest published monthly entry rate across the 9 agentic AI platforms that publish a rate.

Where Google Vertex AI Agent Builder sits in the cluster
OpenAI $0.1Google Vertex AI Agent Builder $1.5Artisan $250
Google Vertex AI Agent Builder sits at $1.5 versus a median of $20 across 9 published rates.

Direct answer

Direct answer

What does Vertex AI Agent Builder charge per token and per grounded query?

Per-token Gemini pricing plus per-query grounding meters. No flat platform fee, but every grounded answer adds a search line on top of the token line.

Direct answer

Best for

Teams building grounded agents on Google Cloud who want Gemini, Vertex Search, and Google grounding in one platform.

Tier table

Each row is a published plan. Quote-only tiers are flagged; we do not infer the price.

PlanMonthlyUnitIncludes
Gemini 3.5 FlashQuote onlyper 1M input tokensGlobal: $1.50 input, $9.00 output per 1M tokens, cached input $0.15. Non-global: $1.65 / $9.90 / $0.165.
Grounding with Google SearchQuote onlyper 1,000 queries5,000 grounding queries per month free across all Gemini 3 models, then $14 per 1,000. Billed only when a grounding prompt returns sources.
Grounding with your dataQuote onlyper 1,000 prompts$2.50 per 1,000 prompts via Vertex Search.
Verified 2026-09-23. Source: cloud.google.com

Hidden costs

Hidden cost 1

Grounding with Google Search bills $14 per 1,000 grounding queries above the first 5,000 free per month, aggregated across all Gemini 3 models. Billing started 5 January 2026.

Hidden cost 2

Grounding with Google Maps is a separate meter on the same terms: 5,000 queries a month free, then $14 per 1,000.

Hidden cost 3

Grounding with your own data via Vertex Search bills $2.50 per 1,000 prompts on top of model and storage cost.

Hidden cost 4

Production Gemini 3.5 Flash output at $9 per million tokens dominates cost for agents that emit long-form responses, and non-global regions add 10% ($1.65 input, $9.90 output).

Related vertical context

Same vendor-neutral discipline applied to adjacent buyer questions in this category.

Verification

2026-09-23
Verified on
Date of last manual check
Published
Pricing posture
Vendor public page status
per token
Pricing model
3
Tiers tracked

Source URL: https://cloud.google.com/vertex-ai/generative-ai/pricing

Last verified 23 September 2026