Batch summaries
100k input tokens and 50k output tokens for a content batch.
Model calculator
Gemini Token Calculator
Estimate Gemini token costs and compare Google's Pro, Flash, and Flash-Lite models for one workload.
Pricing table last updated: 2026-05-13
Interactive tool
Convert tokens to cost
Use presets, share the exact inputs, and scan the live breakdown.
Estimated total cost$0.80
Cost per 1k tokens$0.0053
Examples
Short support reply
2,000 prompt tokens and a compact 300-token answer.
Gemini 3.1 Pro Preview: $2.00 input / $12.00 output per 1M tokens.
How this Gemini Token Calculator works
How Gemini counts tokens
Google's tokenizer differs from OpenAI's and Anthropic's, so token counts for identical text won't match across providers. The Gemini API returns usage metadata with exact counts per request; the rough four-characters-per-token guide helps for early English planning. For multimodal prompts Google counts images, audio, and video on their own terms — this calculator focuses on text input and output.
Choosing the right Gemini model
The ladder runs from Gemini 3.1 Pro for the most capable text work, to Gemini 3 Flash for fast general-purpose use, to Gemini 3.1 Flash-Lite as the lowest-cost tier for very high volume. Output is priced above input across the lineup, so Flash and Flash-Lite are especially attractive for generation-heavy features — compare them against Pro in the calculator above.
Long context and what's excluded
Google publishes separate, higher rates for very long-context requests, which this short-context baseline does not apply. The estimate also excludes context caching, the Batch API, search grounding, and any multimodal usage. Treat it as a planning baseline and confirm current rates on Google's pricing page.
Examples
Gemini 3.1 Flash-Lite · very large batch of short records. Lowest per-token price for high volume.
Gemini 3 Flash · 2,000 input / 500 output per turn. Fast, low-cost general-purpose use.
Gemini 3.1 Pro · output-heavy content. Output cost dominates; mind long-context rates.
FAQ
Are these AI costs exact?
They are estimates based on public token prices. Your bill can change with cached tokens, batch discounts, image or audio usage, taxes, provider credits, and model-specific rules.
Which currency does the calculator use?
All calculators use USD by default because major AI providers publish API pricing in USD.
Why is Gemini Flash-Lite so cheap?
Flash-Lite is Google's lightweight, high-throughput tier built for very high-volume, lower-complexity work. It trades some capability for the lowest per-token price in the Gemini lineup.
Does Gemini count tokens like GPT?
Not exactly. Google's tokenizer differs from OpenAI's, so token counts for the same text can vary. Read the usage metadata the Gemini API returns to measure precisely.
What about Gemini long-context pricing?
Google lists separate, higher rates for very long-context requests. This calculator uses standard short-context text pricing, so very large prompts can cost more than shown.