TokenSave logo TokenSave
100% in-browser · Nothing is uploaded

Gemini Token Counter & API Cost Calculator

Count tokens and see what Gemini 4 Argon, Gemini 3.1 Pro, 3.8 Flash and Flash-Lite charge for your prompt, in any language.

The same text can use from 3% (Chinese) to 144% (Punjabi) more tokens than English — see how we measured 41 languages.

How we measured →

🔍 See how it splits into tokens

Each colour is one token (GPT-4o and later). Boxes with a dashed outline are a single character that takes several tokens.

Colours just split tokens. Same price each: more boxes = higher cost.

Official pricing & tokenizer references:

How do I count tokens for Gemini?

Paste your text above with the Gemini tab selected. You get the token count, characters and the input and output cost on Gemini 4 Argon, 3.1 Pro, 3.8 Flash and Flash-Lite. For Google's exact number, call countTokens in the Gemini API.

Does Gemini use the same tokenizer as GPT?

No. Gemini has its own tokenizer and usually needs about 5% fewer tokens than GPT for the same English text. This counter applies that difference to its estimate.

How much does Gemini cost per token?

Per million input / output tokens: Gemini 4 Argon $2 / $10; Gemini 3.1 Pro $2 / $12; Gemini 3.8 Flash $0.75 / $3.75; Gemini 3.5 Flash-Lite $0.3 / $2.5; Gemini 3.1 Flash-Lite $0.25 / $1.5.

What is the Gemini 4 Argon introductory price?

At launch Gemini 4 Argon is $2 per million input tokens and $10 per million output tokens, half its standard $4 / $20. Google has not announced when the introductory rate ends.

Is my text sent anywhere?

No. The count runs in your browser and your text is never uploaded.

How Gemini counts tokens

Google does not publish Gemini's tokenizer as a library. For English text it produces slightly fewer tokens than GPT, about 5% fewer, and this counter applies that difference, so the Gemini numbers above are a close estimate. For the exact count of one request, the Gemini API has a countTokens method you can call before sending.

Gemini 4 Argon, Google's newest top model (announced September 30, 2026), launched at an introductory price of $2 input / $10 output per million tokens, moving later to a standard $4 / $20. Google has not said how long the introductory rate lasts; the table below uses the standard price. Cached input on Argon is 95% off the normal input price.

For high-volume work the Flash models are where Gemini is cheapest: Gemini 3.1 Flash-Lite costs a sixteenth of Argon's standard input price.

Gemini API prices

ModelInput / output per 1M1,000 chat requests
Gemini 4 Argon$2 / $10$7.00
Gemini 3.1 Pro$2 / $12$7.80
Gemini 3.8 Flash$0.75 / $3.75$2.62
Gemini 3.5 Flash-Lite$0.3 / $2.5$1.45
Gemini 3.1 Flash-Lite$0.25 / $1.5$0.97

Chat request = 1,500 input + 400 output tokens of English text, after Gemini's tokenizer difference. Standard list prices, no caching or batch discounts. (2026-10-14)

More on Gemini costs