AI Cost Calculators
Gemini API Cost Calculator
Estimate Google Gemini API costs using input tokens, cached input, output tokens, Batch API, prompt size, and monthly usage.
Enter Your Gemini API Usage
Use average token values for one request, then enter the expected number of requests in one month.
Price used per 1 million tokens
Input:$1.50
Cached:$0.15
Output:$9.00
Estimated Gemini API Cost
This estimate covers the token charges entered above.
Estimated monthly cost
Per request
$0.004995
Per day
$9.99
Per year
$3,596.40
Uncached input cost
54,000,000 tokens
$81.00
Cached input cost
18,000,000 tokens
$2.70
Output cost
24,000,000 tokens
$216.00
Requests: 60,000
Total input tokens: 72,000,000
Total output tokens: 24,000,000
* Important: Built-in Gemini rates were checked on June 19, 2026. Cache storage, grounding, media, taxes, discounts, and other services are not included.
Gemini API costs can change with the model, prompt size, output length, cached input, and pricing mode. This calculator brings those values together so you can test a small launch, a normal month, and a higher-usage case before you build.
How the Gemini API Cost Calculator Works
Choose a Gemini model and enter the average input and output tokens used by one request. You can also enter the share of input tokens that may use cached pricing.
Enter the number of requests expected in one month. The calculator shows uncached input cost, cached input cost, output cost, and the total cost per request, day, month, and year.
For Gemini Pro models with long-context tiers, select whether the prompt is up to 200,000 tokens or above 200,000 tokens because the official token rates are different.
What to Enter for a Useful Estimate
Use average values from a real request. Include the system message, prompt, chat history, retrieved text, image or document tokens, and other content sent to the model.
For output, include the answer and any thinking tokens that are billed as output. Longer answers and larger thinking budgets can increase the final cost.
Test at least three cases: a small launch, a normal month, and a busy month. This gives you a clearer view of how the cost may grow.
Common Ways to Use This Calculator
- Estimate the monthly cost of a Gemini chatbot.
- Compare current Gemini Pro, Flash, and Flash-Lite models.
- Test the possible saving from cached input.
- Compare Standard and Batch API pricing.
- Review the effect of prompts above 200,000 tokens.
- Prepare an early Google AI API budget.
Simple Gemini API Cost Example
Imagine an AI assistant with 60,000 requests per month. Each request uses 1,200 input tokens and 400 output tokens. If 25% of the input may use cached pricing, enter those values and choose Gemini 3.5 Flash.
The result shows the separate input, cached input, and output costs. You can then switch to Gemini 3.1 Pro Preview or Gemini 3.1 Flash-Lite without changing the workload.
Pricing and Estimate Notes
Built-in prices were checked against Google's official Gemini Developer API pricing page on June 19, 2026. Google may change models, prices, limits, or billing rules at any time.
This calculator covers the token charges entered above. Context cache storage, Google Search grounding, Google Maps grounding, images, audio, video, taxes, and other services may add separate costs.
Always check the official Gemini API pricing page before making a final budget or purchase decision.
Frequently Asked Questions
How is Gemini API cost calculated?
The calculator multiplies input, cached input, and output tokens by the selected Gemini model rates. It then shows the estimated cost per request, day, month, and year.
What are cached input tokens in Gemini?
Cached input tokens are tokens reused from stored context. They can use a lower token rate, but context cache storage may create a separate hourly charge that is not included in this calculator.
Why do some Gemini Pro models have two price levels?
Gemini 3.1 Pro Preview and Gemini 2.5 Pro use one rate for prompts up to 200,000 tokens and a higher rate for prompts above 200,000 tokens. Choose the matching prompt size in the calculator.
Does Gemini Batch API cost less?
Yes. Google lists lower Batch API token rates for supported Gemini models. The calculator uses the official Batch rates for the selected model.
Are thinking tokens included in the output price?
Yes. Google's pricing page states that output pricing includes thinking tokens for these Gemini models.
Are the results exact?
No. They are planning estimates. Your final bill may change because of price updates, grounding, cache storage, images, audio, tools, taxes, discounts, or other services.