Free calculator
Gemini API pricing calculator
Your monthly Gemini bill on each model at Google's paid-tier prices, with the two increases Google has already announced. Pick a date and see what the same traffic costs then.
How much does the Gemini API cost? (prices checked 2026-10-25)
Gemini 3.8 Flash is $0.75 per million input tokens and $3.75 per million output tokens until December 31, 2026, then $1.50 and $7.50. Gemini 4 Argon is $2 and $10 until November 30, 2026, then $4 and $20. Gemini 3.5 Flash-Lite stays at $0.30 and $2.50. Batch is half price, and Search grounding on Gemini 3 and newer costs $14 per 1,000 searches after 5,000 free a month.
| Model | Tokens | Search | Per month | vs today |
|---|
Paid-tier list prices from ai.google.dev/gemini-api/docs/pricing (updated 2026-10-22), checked 2026-10-25; 30-day month; text, image and video input up to 200k tokens per prompt (audio input costs more on some models). Search grounding: Gemini 3 and newer are billed per search query the model runs, with 5,000 free a month shared across those models, then $14 per 1,000. Gemini 2.5 models get 1,500 grounded prompts a day free, then $35 per 1,000 (counted here as one search per prompt). Explicit cache storage per hour, Maps grounding and the free tier are not included.
Why this line grows
Output tokens are the expensive side on every Gemini model, five to eight times the input price, and thinking tokens are billed as output. A model that thinks for 2,000 tokens before writing a 300-token answer is billed for 2,300 output tokens. If your bill is mostly output, look at the thinking budget before you look at a cheaper model.
The other line people miss is Search grounding. On Gemini 2.5 Flash the first 1,500 grounded prompts a day are free. On Gemini 3 and newer, the free allowance is 5,000 searches a month for the whole project, and the model can run more than one search for a single prompt. An app that grounds 1,000 prompts a day pays nothing for search on 2.5 Flash and about $350 a month on 3.5 Flash-Lite. Set the search field to your own number and switch models in the table.
Our Gemini API pricing post goes through the December and January increases and what to do about them. The LLM API cost calculator puts the same traffic next to Claude and OpenAI.
If your AI bill grew faster than your users, send us the usage page.