Gemini Cost Calculator

Work out Gemini API costs across the Pro and Flash tiers. Enter token counts and daily volume to see the monthly total, and compare tiers by switching the model.

Inputs

Result

$270

per month

$0.0090 per request · $9.00 per day · $3,285 per year

Input cost per request
$0.0030
Output cost per request
$0.0060
Cost per 1,000 requests
$9.00
Tokens per day
2,000,000
Tokens per month
60,000,000
Cost per day
$9.00
Cost per month (30 days)
$270
Cost per year
$3,285

Disclaimer: Model availability, pricing and specifications may change. Verify pricing directly with the provider before making business decisions. Preset rates reflect published list prices last reviewed August 2026; choose “Custom pricing” to enter your own rates.

Formula

  • Request cost = (input tokens × input rate + output tokens × output rate) ÷ 1,000,000
  • Monthly cost = request cost × requests per day × 30

Methodology

Pricing is quoted per million tokens and split into input (what you send, including the system prompt and any retrieved context) and output (what the model writes back). The two rates are different, and output is usually the more expensive of the pair.

The calculator multiplies your token counts by the selected rate, then scales the per-request cost by your daily volume to a monthly and annual figure. A 30-day month and a 365-day year are used so results stay comparable between tools.

Provider prices change, so every model list includes a custom option. Enter the exact rates from your provider's pricing page for a number you can put in a budget. Model availability, pricing and specifications may change. Verify pricing directly with the provider before making business decisions.

Example: high-volume classification on Flash

  1. A classifier sends 600 input tokens and returns 40 output tokens, 50,000 times a day, on Flash ($0.075 / $0.30 per million).
  2. Per request: (600 × $0.075 + 40 × $0.30) ÷ 1,000,000 = $0.000057.
  3. That is about $2.85 a day and roughly $85 a month for 50,000 daily calls.

Frequently asked questions

What is the difference between the Pro and Flash tiers?

Flash is optimised for speed and price and handles classification, extraction and routine generation well. Pro costs more per token and is worth it for harder reasoning, longer chains and higher-stakes output.

Is there a free tier?

Google has historically offered a rate-limited free tier for evaluation. It is fine for prototyping but not for production traffic, so budget with the paid rates shown here.

How are images and audio billed?

Multimodal inputs are converted into a token equivalent before billing. Check your provider's conversion table, then enter the resulting token count in the input field.

Are these prices always up to date?

The presets reflect widely published list prices and are reviewed periodically, but providers adjust them and offer discounts for batch processing, cached input and committed spend. Model availability, pricing and specifications may change. Verify pricing directly with the provider before making business decisions.

What happens when a provider launches a new model?

Model names and rates live in one central configuration, so a new model appears in every relevant dropdown as soon as it is added. Page URLs stay provider-based rather than version-based, so no link ever goes stale when a model generation changes.

Does the calculator send my data anywhere?

No. Every calculation runs in your browser, so nothing you type is uploaded, stored or logged.

Related AI calculators