Tools Web

Calculators

Gemini Batch API Savings Calculator

Price the same Gemini load on Standard, Batch, and Flex. Pick Gemini 4 Argon or 3.8 Flash, enter monthly input and output tokens, and toggle post-promo rates (Argon from 2026-12-01; Flash from 2027-01-01). Batch and Flex are ~50% of Standard on the Paid table. Estimates only; official Gemini pricing prevails.

Math runs in your browser. Nothing is uploaded.

Custom $/1M rates (optional)

Standard monthly USD
—

Batch monthly USD
—

Flex monthly USD
—

Batch savings vs Standard
—

Flex savings vs Standard
—

Estimates only; official vendor pricing prevails (2026-10-30). Each tier = input ÷ 1M × in rate + output ÷ 1M × out rate. Batch and Flex ≈ 50% of Standard on the Paid table. Carbon is FAQ-only (Paid API unstable).Official pricing: Gemini

Gemini Token Cost Calculator · OpenAI Batch API Savings Calculator · OpenAI Flex vs Fast vs Standard Cost Calculator · LLM API Cost Calculator

More in this group

How it works

How is Gemini Batch vs Flex savings calculated?
Each tier = input ÷ 1M × input $/1M + output ÷ 1M × output $/1M. Savings = Standard − Batch (or Flex). Example: Argon promo, 10M in / 2M out → Standard $40, Batch/Flex $20 (−50%).
What are Argon and Flash promo cliffs?
Gemini 4 Argon Standard $2/$10 → $4/$20 from 2026-12-01; Batch/Flex $1/$5 → $2/$10. Gemini 3.8 Flash Standard $0.75/$3.75 → $1.50/$7.50 from 2027-01-01; Batch/Flex ≈ half. Toggle post-promo rates to price the cliff.
Is Gemini Carbon included?
No hard Carbon slug or model preset. Paid API listing for Carbon was still unstable at snapshot time—treat Carbon as FAQ signal only until Google publishes a stable Paid row.
How does this compare to OpenAI Batch/Flex?
Use the OpenAI Batch API savings and Flex vs Fast calculators for OpenAI’s table. This page is Gemini-only.
Are results billing-grade?
No. Estimates only; official Gemini pricing prevails.