1. Blocks
  2. Gemini API

Gemini API

Google's Gemini models, called from your server while the app runs.

Priced from vendor pages
Prices checked
20 Oct 2026
Sources
1
How we check

What it is

The Gemini API gives your app Google's Gemini models, priced per million tokens read and written. Most models have a free tier for testing, but Google says data sent on the free tier is used to improve its products. Paid usage isn't.

Good for

  • Testing an AI feature for free before you pay
  • A mid-tier model (Gemini 3.8 Flash) priced below OpenAI's and Anthropic's mid-tier models, until January 2027

Watch out for

  • Free-tier prompts and answers can be used to improve Google's products
  • Gemini 3.8 Flash doubles in price on 1 January 2027
  • Grounding with Google Search is billed separately after 5,000 free requests a month

In comparisons

OpenAI vs Claude vs Gemini APIs for a chat feature

Small: gemini-3.1-flash-lite ($0.25 in / $1.50 out per million tokens). Mid: gemini-3.8-flash ($0.75 / $3.75, then $1.50 / $7.50 from 1 Jan 2027)

  • The cheapest mid-tier model for now, and a free tier on both models for testing.

Free-tier data is used to improve Google's products; paid data isn't. Gemini 3.8 Flash doubles in price on 1 January 2027.

Newsletter

Stackable by Stackguide

Price changes on the blocks you use, and new builds, by email.

Build

Directory site with paid listings

A searchable, SEO-friendly niche directory where businesses pay by card to submit or feature a listing.

See the build

Compare

OpenAI vs Claude vs Gemini APIs for a chat feature

What does an AI chat feature cost each month in API fees?

Read the answer