—per day
—per 1k requests
—vs GPT-4o / mo
Gemini vs the field — same workload
Identical tokens and volume, priced on each model.
| Model | Input $/1M | Output $/1M | Cost / month |
|---|
⚠️ Gemini reference pricing (July 2026): 2.5 Pro $1.25/$10, 2.5 Flash $0.30/$2.50, 2.0 Flash $0.10/$0.40 per 1M tokens. The free tier (AI Studio) has rate limits, not token charges. Confirm on Google's pricing page. See every provider on the
full AI API cost calculator. ·
Report outdated price →✓ Last verified: 2026-08-15· Source: official provider pricing page· Auto-monitored — report change →
The free tier comes first
Gemini is unusual among the big models: it has a genuine free tier through Google AI Studio, with no credit card to start. It's capped by requests-per-minute and requests-per-day rather than tokens, so for prototypes and many low-traffic apps the honest answer is you may pay nothing. This calculator shows the paid-tier bill — what you'd owe once you exceed the free limits and switch to pay-as-you-go.
When you do pay, Gemini is one of the cheapest capable options. 2.0 Flash ($0.10 / $0.40) is astonishingly cheap for high-volume work, 2.5 Flash ($0.30 / $2.50) adds capability, and 2.5 Pro ($1.25 / $10) competes with frontier models at a lower input price. As always, output is the costly side — cap answer length first. Comparing providers? Put Gemini against GPT-4o and Claude on the AI API cost calculator, price a feature with the AI app cost estimator, and get your key via the Gemini guide.
How this calculator works
The Gemini API Cost Calculator estimates what you would pay to run Google's Gemini models based on your own usage. You pick a model — 2.5 Pro, 2.5 Flash, or 2.0 Flash — and enter your requests per day, input tokens per request, and output tokens per request. It multiplies your token volume by each model's separate input and output rates to project a monthly cost, and flags whether the free tier already covers your workload. The main cost drivers are your model choice, daily request count, and how many tokens each request reads and writes.
The key trade-off is capability versus price: 2.5 Pro costs more per token than the Flash models, so a heavy prompt or long output on Pro adds up fast. Because output tokens are typically priced higher than input, trimming verbose responses often saves more than shortening prompts. Check the free-tier result before assuming you owe anything at low volume.
Frequently asked questions
Does Gemini have a free API tier?
Yes. Google AI Studio offers a genuine free tier for the Gemini API with per-minute and per-day rate limits, and no credit card required to start. It's enough for prototypes and many low-volume production apps. Paid tier removes the limits and is billed per token.
How much does the Gemini API cost?
Reference pricing (July 2026): Gemini 2.5 Pro about $1.25 input / $10 output per million tokens, Gemini 2.5 Flash about $0.30 / $2.50, and Gemini 2.0 Flash about $0.10 / $0.40 — among the cheapest capable models available.