Quota Monitor
Checking sign-in status…

Gemini API Pricing & Cost Calculator (Oct 2026)

Compare selected Gemini Developer API paid text models using Google's official rates. These are direct Developer API prices; Vertex AI, consumer subscriptions, and Live audio use different pricing scopes.

Gemini API prices per million tokens (USD)

ModelInputCached inputOutputBatch inputBatch output
gemini-4-argon$2.00$0.10$10.00$1.00$5.00
gemini-3.8-flash$0.75$0.075$3.75$0.375$1.875
gemini-3.6-flash$0.75$0.075$3.75$0.375$1.875
gemini-3.5-flash-lite$0.30$0.03$2.50$0.15$1.25
Official Gemini API pricing(opens in a new tab)

Estimate your Gemini API cost

Estimated cost$40.00

Uses official list prices for input and output tokens only. Cache, long context, tools, regional uplifts, taxes, and discounts are excluded.

Compare models with cache-aware estimates

How Gemini API billing works

  • Prices are USD per million tokens. Output includes billable thinking tokens. Enter the total billable output, not just the visible answer.
  • The Argon rates shown apply through November 30, 2026; its listed input, output, and cached-input rates double on December 1. Argon supports implicit caching only.
  • The Flash 3.8 and 3.6 rates shown apply through December 31, 2026; their listed token rates double on January 1, 2027. This page is a dated price snapshot, not a quote for later billing periods.
  • Explicit cache storage is extra: Flash 3.8/3.6 costs $0.50 per million cached tokens per hour through December 31, 2026, then $1.00. Flash-Lite 3.5 storage is $1.00 per million tokens per hour. Storage is excluded from the calculator.
  • Grounding, search, audio/video, images, Live API, taxes, and negotiated discounts are excluded. Free-tier quotas and eligible models vary; the calculator uses paid rates without subtracting a free allowance.
  • The simple Batch estimate covers uncached input and output only. Do not apply standard cached-input rates to Batch requests; consult the separate Batch caching rates in the source.

Track Gemini API costs before limits stop requests

Quota Monitor reads Gemini Developer API project costs and Spend Cap information through a preview reporting API; verification with a real account is still pending and costs can be delayed. It does not read prepaid credit balances or the remaining allowance of a consumer Gemini subscription.

Read the Gemini API monitoring guide

Gemini API pricing FAQ

Is the Gemini API free?
Some models have a limited free tier. Eligibility and quotas depend on the model and account. This page uses paid-tier rates so that a production estimate does not assume free quota.
Why is my Gemini bill higher than the token estimate?
Check thinking tokens, cache storage duration, grounding and search usage, the billing tier, and the rate effective on the request date. These can differ from a basic text-token estimate.
Does a Google AI subscription pay for API usage?
Do not treat a consumer subscription allowance as Developer API credit. Verify the project's API billing configuration and the terms of the specific plan.

More articles