Gemini Token Cost Calculator

Model prices are illustrative reference points and change over time — verify current rates at ai.google.dev/pricing, or choose "Custom Rate" to enter your own.

Related Calculators

Claude Token Cost Calculator IP Subnet Calculator Cloud Cost Calculator Frame Rate Calculator

Prompt Tokens and Response Tokens, Priced Apart

Google's Gemini API, like other major LLM APIs, bills the tokens you send and the tokens the model returns at different per-token rates, with output tokens generally the more expensive of the two. Gemini's model lineup spans everything from lightweight "Flash" variants built for high-throughput, low-latency tasks to larger "Pro" models for more demanding reasoning, and the price gap between tiers can be substantial — which makes it worth checking the actual cost impact before defaulting to the largest available model.

The Formula

Input Cost = (Input Tokens ÷ 1,000,000) × Price per 1M Input Tokens
Output Cost = (Output Tokens ÷ 1,000,000) × Price per 1M Output Tokens
Total Cost = Input Cost + Output Cost

Token counts are converted to millions before being multiplied by the applicable per-model rate, then the input and output costs are added for the total.

Where This Calculation Matters

  • Flash vs. Pro tradeoffs — running the same token counts through a Flash-tier and a Pro-tier model shows the concrete dollar cost of choosing the more capable model for a given task.
  • High-volume application budgeting — Flash-tier models are frequently chosen specifically for cost efficiency at scale; this calculator quantifies exactly what that efficiency is worth at your expected volume.
  • Multimodal and long-context planning — Gemini's larger context windows can mean substantially higher input token counts per call than a typical text-only prompt, which changes the cost profile meaningfully.
  • Migration cost comparisons — teams evaluating a move to or from Gemini can compare like-for-like token costs against another provider's calculator.

Why the Model Selector Matters

The dropdown includes several current Gemini model families with built-in per-model input/output rates, plus a "Custom Rate" option to enter your own pricing for a model not listed or a rate you've confirmed separately.

Note: Google's published Gemini API pricing changes over time and varies by model tier and context length. The rates built into this calculator are reference points, not a live feed — always confirm current pricing at ai.google.dev/pricing before budgeting a production workload, or use the Custom Rate option with a rate you've verified yourself.

How to Use This Calculator

  1. Select a Model from the dropdown, or choose "Custom Rate" to enter your own pricing.
  2. If using Custom Rate, enter the Custom Input Price and Custom Output Price per 1M tokens.
  3. Enter the Input Tokens count for your request.
  4. Enter the Output Tokens count for the expected or actual response.
  5. Select Calculate for the total estimated cost, broken down by input and output.

Related Calculations

Estimate a token count first with the AI Token Calculator, or compare pricing against other providers with the Claude Token Cost Calculator and the OpenAI Token Cost Calculator.