Gemini API Cost Calculator

Estimate Google Gemini 2.5 Pro, Flash and Flash-Lite costs.

Quick answer

With the default inputs, $0.00625 per request — ~$187.50/month at 1,000 requests/day. Enter your own numbers below to recompute instantly; the full step-by-step math is shown under the worked example.

Gemini model

Input tokens(tokens)

Output tokens(tokens)

Results update automatically as you type.

Result

$0.00625 per request

~$187.50/month at 1,000 requests/day

Input cost: $0.00125
Output cost: $0.00500
Per request: $0.00625
Per day: $6.25
Per month: $187.50

Estimate the cost of Google's Gemini API for the 2.5 Pro, Flash and Flash-Lite models. Enter your tokens and volume to see per-request and monthly cost. Note that Gemini Pro pricing steps up above 200K input tokens.

How this is calculated

Cost per request = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price) for your chosen Gemini model. Note Gemini 2.5 Pro steps up to a higher rate once a prompt exceeds 200K input tokens; this uses the base rate, so very long prompts cost more. Monthly cost scales by requests per day × 30.

Is this a good result? What to do next

Flash-Lite is the lowest-cost route, Flash is cheap, and Pro is reserved for the hardest reasoning and longest documents. The gotcha is the 200K long-context step-up on Pro — if your prompts are large, budget at the higher tier.

Typical planning ranges

Gemini 2.5 Flash-Lite: lowest cost
Gemini 2.5 Flash: cheap mid-tier
Gemini 2.5 Pro >200K input: higher long-context rate

Ranges are typical planning figures to sanity-check your result, not authoritative benchmarks. Your numbers will vary with use case, volume, and vendor.

How to improve this number

Route most traffic to Flash or Flash-Lite.
Keep prompts under 200K tokens to avoid the Pro step-up.
Use caching and batch pricing where available.

Common mistakes

Using the base rate to budget prompts over 200K tokens.
Overusing Pro when Flash handles the task.

When to use a different approach

To compare Gemini against GPT and Claude, use the model cost comparison. For long-document planning, use the context window planner.

Worked example (defaults)

With the default inputs above, here is the result:

Result

$0.00625 per request

~$187.50/month at 1,000 requests/day

Input cost: $0.00125
Output cost: $0.00500
Per request: $0.00625
Per day: $6.25
Per month: $187.50

input: 1,000 / 1e6 x $1.25/M = $0.00125
output: 500 / 1e6 x $10/M = $0.00500
monthly = $0.00625 x 1,000 x 30 days

Sources & references

Frequently asked questions

Why does Gemini Pro have two prices?+

Gemini 2.5 Pro charges more once a prompt exceeds 200K input tokens ($2.50 input / $15 output per 1M vs $1.25 / $10). This tool uses the base rate; large prompts cost more.

Which Gemini model is cheapest?+

Gemini 2.5 Flash-Lite is the lowest-cost route, followed by Flash. Pro is reserved for the hardest reasoning and longest documents.