Input vs output token spend
Output tokens usually cost several times more than input, so answer length is what really drives your bill.
Home / Dev & AI / AI & LLM Cost / Gemini API Cost Calculator
AI & LLM Cost
Gemini API Cost Calculator
Estimate your Google Gemini bill instantly. Choose a Gemini model, enter your request volume and token sizes, and see the monthly cost with a comparison across the Gemini 2.5 family for 2026.
Estimated monthly cost
$0
Cost per request—
Cost per 1,000 requests—
Input token cost—
Output token cost—
Tokens processed / month—
Annual estimate—
The same workload priced across AI models
Your monthly token volume run through popular 2026 models, cheapest first.
What the Gemini API Cost Calculator does
Google bills the Gemini API per token, and the 2.5 family spans a wide price range. Gemini 2.5 Flash-Lite is built for the highest volume, cheapest tasks, Gemini 2.5 Flash is the fast everyday model, and Gemini 2.5 Pro is the flagship for complex work. Flash and Flash-Lite are among the most affordable capable models available, which makes Gemini popular for high traffic apps.
This Gemini API cost calculator prices your workload on the model you pick and compares it across the whole 2.5 lineup, so you can see how much you save by keeping routine traffic on Flash and only escalating to Pro when a task truly needs it.
Heads up on pricing. The rates built into this tool are public list estimates for July 2026 and can change without notice. Providers also offer batch discounts, prompt caching and volume tiers that lower real costs, so treat the output as a planning estimate, not a quote.
The formula
cost = (input tokens ÷ 1M × input rate) + (output tokens ÷ 1M × output rate)
Gemini 2.5 Flash: $0.30 input, $2.50 output per million tokens
Gemini 2.5 Flash: $0.30 input, $2.50 output per million tokens
Worked example
On Gemini 2.5 Flash, 250,000 requests a month at 1,500 input and 350 output tokens cost 375M × $0.30 + 87.5M × $2.50 per million = $112.50 + $218.75 = about $331 a month. On Gemini 2.5 Pro the same traffic is roughly $1,344.
Gemini API pricing used (per 1M tokens, July 2026 estimates)
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Gemini 2.5 Pro | $1.25 | $10.00 |
| Gemini 2.5 Flash | $0.30 | $2.50 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 |
July 2026 list estimates. Gemini 2.5 Pro charges a higher rate for very long context prompts above its standard threshold. Batch mode and caching lower real costs.
Ways to lower your AI costs
- Match the model to the task. Route simple requests to a small model like GPT-5 mini, Gemini Flash or DeepSeek V3, and keep premium models for complex reasoning where quality pays off.
- Cache repeated context. Prompt caching means you stop paying full price for the same system prompt or documents on every call.
- Cap output length. Output tokens cost several times more than input, so limiting response length is often the fastest saving you can make.
- Trim prompts and history. Summarize old conversation turns and drop context the model does not actually need to answer well.
- Batch non-urgent work. Many providers offer batch pricing at around half the standard rate for jobs that can wait a few hours.
Frequently asked questions
How much does the Gemini API cost in 2026?
Gemini 2.5 Flash is about $0.30 per million input tokens and $2.50 output, among the cheapest capable models. Enter your usage above for a monthly total.
What is the cheapest Gemini model?
Gemini 2.5 Flash-Lite at roughly $0.10 input and $0.40 output per million tokens, ideal for very high volume, simple tasks.
Does Gemini charge more for long context?
Gemini 2.5 Pro applies a higher rate once a prompt exceeds its standard context threshold. For typical prompt sizes the standard rate in this tool applies.
Is Gemini cheaper than GPT-5 and Claude?
On the Flash tiers, usually yes by a wide margin. Gemini 2.5 Pro is priced similarly to GPT-5. Compare on your own tokens to confirm.
Are these rates official?
They are July 2026 list estimates. Check the Google AI pricing page for current official rates.