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.
Tell us what you do
Based on observed usage samples and official pricing. Switch to measured usage when you have countTokens or usageMetadata.
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.
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 storageEvery token quantity is multiplied by its model and processing-mode rate. Explicit cache storage uses cached token-hours.
Standard vs Batch
Standard is for interactive requests. Batch processes asynchronous workloads and uses the model’s separately published Batch rates.
Caching
Cache hits use the cached-input rate. Explicit caches also add a storage charge based on token count and time-to-live.
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
1M input + 200k output
$1.50 / month10M input + 1M output
$2.75 / month5M cached input + 500k output
$2.25 / monthFor the most accurate result: use Google’s official countTokens API before a request, or copy actual token counts from usageMetadata after it runs.