ai apis / google (gemini) / gemini api
What the Gemini API really costs
200,000 requests a month to a model cost $0.00 a month, or $0 a year.
list prices, read from the providers' pages · checked 17 november 2026 · sources
model provider
a year $0
you can keep
$0.00 a month
That is what the Batch API would save on this model: a month instead, for work that can wait up to a day.
Why the bill is bigger than expected
Several prices double soon. Google has announced that Gemini 4 Carbon and Argon double their prices on 1 December 2026, and Gemini 3.8 and 3.6 Flash on 1 January 2027. The sheet applies each change from its date and shows the next price under the output line.
Thinking tokens are output. Gemini models that reason bill their thinking tokens as output, at the output price. A short answer can still carry many billed output tokens.
Batch costs half. Batch requests are billed at half the standard price, for results returned within 24 hours. The free tier has lower limits and its data may be used to improve Google products.
Sources
- [1]Google API prices per million tokens, standard, cached and batch, as published. ai.google.dev/gemini-api/docs/pricing, read 2026-11-17.
Prices are list prices in USD per million tokens, before tax, credits or committed-use discounts. They are kept by hand from each provider's pricing page and confirmed against it every night; a price that no longer matches blocks the site from updating. Cache writes, tools such as web search, images, audio and fine-tuning are not counted. The calculator runs in your browser; nothing you type is sent anywhere.