GOOGLE GEMINI API · USAGE-AWARE

Gemini API Cost Calculator

Estimate Gemini 3.6 Flash costs from writing, summarization, coding, or research tasks—or enter measured tokens for Standard, Batch, caching, thinking, and storage pricing.

Official Google pricingVerified October 11, 2026USD · Gemini Developer API
Pricing mode
Billing tier
SIMPLE ESTIMATE

Tell us what you do

Based on observed usage samples and official pricing. Switch to measured usage when you have countTokens or usageMetadata.

SAME TASK · OFFICIAL PRICING

Compare estimated cost ranges

These ranges use each measured model’s observed usage for the same task, size, and count. They do not compare quality or speed.

OpenAI · GPT-6 Astra$1.08–$1.09No positive savings range
OpenAI · GPT-6.1 Sol$0.22–$0.23Potential monthly savings: $0.06–$0.11
OpenAI · GPT-6 Luna$0.010–$0.013Potential monthly savings: $0.27–$0.32
Claude · Opus 5.5$0.87–$0.92No positive savings range
Claude · Sonnet 5.5$0.38–$0.42No positive savings range
Claude · Haiku 5.5$0.015–$0.018Potential monthly savings: $0.27–$0.31
Google · Gemini 4 Argon$0.25–$0.26Potential monthly savings: $0.03–$0.08
Google · Gemini 3.8 Flash$0.27–$0.32Potential monthly savings: $0.00–$0.06Ranges overlap; savings are uncertain.

CLEAR PRICING MATH

How Gemini API cost is calculated

Tallyvexa keeps each billable component separate so you can see where your monthly spend comes from.

non-cached input + cached input + (output + thinking) + cache storage

Every token quantity is multiplied by its model and processing-mode rate. Explicit cache storage uses cached token-hours.

01

Standard vs Batch

Standard is for interactive requests. Batch processes asynchronous workloads and uses the model’s separately published Batch rates.

02

Caching

Cache hits use the cached-input rate. Explicit caches also add a storage charge based on token count and time-to-live.

03

Long context

For Gemini 3.1 Pro Preview, the 200k boundary applies per request. Monthly token totals cannot determine the correct tier by themselves.

QUICK EXAMPLES

Example monthly workloads

Gemini 3.6 Flash · Standard

1M input + 200k output

$1.50 / month
Gemini 3.5 Flash-Lite · Batch

10M input + 1M output

$2.75 / month
Gemini 3.8 Flash · Standard

5M cached input + 500k output

$2.25 / month

For the most accurate result: use Google’s official countTokens API before a request, or copy actual token counts from usageMetadata after it runs.