PromptCostLab
Gemini token calculator

Make Gemini context easier to budget.

Measure prompt size, output headroom, and a planning cost for Gemini Pro and Flash routes.

Calculate tokens ↓Compare all models
Gemini 3.1 Pro Preview1,048,576token context window
$2 input / 1M $0.2 cached / 1M $12 output / 1M
Official · verified 2026-08-16View provider pricing ↗Standard price for prompts up to 200K; larger prompts are tiered at $4/$18. Explicit cache storage costs $4.50 per 1M tokens per hour.

What this page helps you decide

  • See context pressure before a large request fails.
  • Choose Pro for quality or Flash for throughput.
  • Use the same prompt measurement workflow across providers.

Prices are planning references, not a billing guarantee. Check the provider’s current pricing before launch.

Estimate a Gemini 3.1 Pro Preview request
1,048,576 context
0input tokens · local estimate
$0.00estimated input cost
$0.0060reserved output cost
$0.0060estimated request total

<0.1% of context reserved. Close approximation · o200k proxy — counts are exact for OpenAI models and a close approximation for Google; provider formatting, tools, and files can change the real count.

The formula

From prompt to request cost

Estimated request cost equals input tokens multiplied by $2 per million, plus expected output multiplied by $12 per million. Cached input is separate only when the provider publishes a rate.

What changes the result

Count the assembled request

System instructions, conversation history, retrieved documents, tool definitions, files, and response length all matter. Use the visible prompt for drafting, then validate the final payload with Google.

Before you rely on the number

Gemini 3.1 Pro Preview calculator questions

Is this Gemini 3.1 Pro Preview token count exact?

No. It is a private plain-text planning estimate. Google tokenization, chat formatting, tools, files, and images can change the real count.

Does the prompt leave my browser?

No. The calculator runs locally in your browser. Only the page itself and published registry data are loaded from PromptCostLab.

How should I verify production cost?

Check the linked Google pricing page, then compare the estimate with token usage returned by the real API request.