Pricing last checked: July 2026. All estimates are in USD.
This Gemini API cost calculator estimates text-token charges for current Google Gemini models. Enter your input, cached-input and output tokens, choose Standard or Batch processing, and multiply by the number of requests.
Google pricing varies by model, tier, modality, context size and optional tools. Confirm every production estimate against the official Gemini Developer API pricing page.
Calculate Gemini API text-token cost
Rates used in the Gemini calculator
| Model | Standard input | Standard output | Batch input | Batch output |
|---|---|---|---|---|
| Gemini 3.6 Flash | $1.50 | $7.50 | $0.75 | $3.75 |
| Gemini 3.5 Flash | $1.50 | $9.00 | $0.75 | $4.50 |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | $0.15 | $1.25 |
| Gemini 3.1 Flash-Lite | $0.25 | $1.50 | $0.125 | $0.75 |
How the estimate works
- Choose a current model. Flash-Lite models target cost-efficient high-volume work, while the Flash models have higher listed rates.
- Select Standard or Batch. Batch processing costs less but is designed for asynchronous work rather than immediate interactive responses.
- Enter token counts. Separate normal input, eligible cached input and output. Google’s listed output rates can include thinking tokens.
- Multiply by requests. Forecast a day, month or project and add headroom for longer prompts, retries and growth.
What is not included
- Grounding with Google Search or Google Maps.
- Context-cache storage charges.
- Priority, Flex, enterprise or volume pricing.
- Audio, image or video-specific token rates.
- Taxes, currency conversion and other cloud charges.
Frequently asked questions
Is the Gemini API free?
Google offers a free tier with limited access and free input and output tokens for certain models. Production workloads may require the paid tier, which provides higher limits and additional capabilities. Check the official pricing page because free-tier eligibility and limits can change.
Does this calculator support images or audio?
No. It estimates text-token pricing only. Some Gemini models price text, image, video and audio input at the same rate; others do not. Use Google’s modality-specific table for mixed-media workloads.
Why did the old character-based estimate disappear?
Current Gemini Developer API pricing is published primarily per one million tokens and varies by model and processing tier. A single per-character rate no longer represents the current product range accurately.
Compare another provider with our OpenAI API cost calculator, or see both tools on the AI cost calculators hub.