Skip to main content
cost.botzone.ai
Sign in

Google

Gemini API cost calculator

Price Gemini usage by the month, in euro, with the arithmetic shown. The Flash models are cheap enough that the interesting question is usually whether Pro is earning its place on a given route.

Nothing here is gated. No signup, no email, no credentials.

Your usage

Change anything here and every number on the right updates straight away.

Rates come from the same published price table Cost uses to price the calls it meters.

The same calls and the same tokens, priced on a second model.

Start from a typical workload

These load ordinary figures for each shape of work. Change any of them below; the sum follows.

Every request your app makes to the model API, across all routes.

System prompt, retrieved context and the user message. Roughly 750 words is 1,000 tokens.

What the model writes back. Output usually costs about five times as much as input.

25%

The share of your input tokens served from the prompt cache. If the model has no published cached rate, this changes nothing and the working says so.

Estimated model spend

€1,248per month

Exact, in euro
€1,248.21
In dollars
$1,356.75
Per call
$0.009045
Per year
€14,979

The working

Every step, in order. If we quoted you a figure by email, this is how we got it.

  1. 1Model: gemini-2.5-pro on Google Gemini.
  2. 2Published rate: $1.25 per 1M input tokens, $10.00 per 1M output tokens, $0.31 per 1M cached input tokens.
  3. 3Usage: 150,000 calls a month, 3,000 input tokens and 600 output tokens per call.
  4. 4Cache: 25% of the input is a cache hit, so 750 tokens are billed at the cached rate and 2,250 at the full input rate.
  5. 5Input per call: 2,250 / 1,000,000 x $1.25 = $0.002812
  6. 6Cached input per call: 750 / 1,000,000 x $0.31 = $0.000233
  7. 7Output per call: 600 / 1,000,000 x $10.00 = $0.006000
  8. 8Cost per call: $0.009045
  9. 9Cost per month: 150,000 x $0.009045 = $1,356.75
  10. 10In euro at 0.92 USD to EUR: $1,356.75 x 0.92 = €1,248.21
  11. 11This counts API token cost only. It does not include cache-write charges, retries, embeddings, batch discounts or anything you spend outside the model API.

Converted at a standing rate of 0.92 USD to EUR. The dashboard uses the live daily rate instead, so your real invoice will differ by a percent or two.

What a cheaper model would cost

gemini-2.5-pro
€1,248.21
gemini-2.5-flash-lite
€28.98

€1,219.23a month less

€14,631 a year

Would quality hold?

On your traffic, nobody knows until it is tested, and an untested switch is a bet against quality. That is usually why the model stays where it is. Cost shadow-runs your real traffic against the cheaper model, scores it with an independent judge across five dimensions, and recommends the switch only once the cheaper model matches on 95% of them.

That is a verified recommendation and a projected saving. It does not switch anything for you. Send a usage export or measure it on the free tier.

The working, compared

The same arithmetic on the second model, and the difference.

  1. 1Compared with: gemini-2.5-flash-lite on Google Gemini, at exactly the same usage.
  2. 2Published rate: $0.04 per 1M input tokens, $0.15 per 1M output tokens.
  3. 3Cost per call on gemini-2.5-flash-lite: $0.000210
  4. 4Cost per month: 150,000 x $0.000210 = $31.50, which is €28.98.
  5. 5Difference: €1,248.21 - €28.98 = €1,219.23 a month cheaper on gemini-2.5-flash-lite.
  6. 6Over twelve months: €1,219.23 x 12 = €14,630.76.
  7. 7Same tokens and the same cache hit rate on both sides. A cheaper model may need longer prompts or more retries, and this does not model output quality.
  8. 8gemini-2.5-flash-lite publishes no cached-input rate, so the cache slider changes nothing on that side.
Show the full sum for gemini-2.5-flash-lite
  1. 1Model: gemini-2.5-flash-lite on Google Gemini.
  2. 2Published rate: $0.04 per 1M input tokens, $0.15 per 1M output tokens.
  3. 3Usage: 150,000 calls a month, 3,000 input tokens and 600 output tokens per call.
  4. 4Cache: gemini-2.5-flash-lite has no published cached-input rate, so a cache hit does not reduce the bill. All 3,000 input tokens are charged at the full input rate.
  5. 5Input per call: 3,000 / 1,000,000 x $0.04 = $0.000120
  6. 6Output per call: 600 / 1,000,000 x $0.15 = $0.000090
  7. 7Cost per call: $0.000210
  8. 8Cost per month: 150,000 x $0.000210 = $31.50
  9. 9In euro at 0.92 USD to EUR: $31.50 x 0.92 = €28.98
  10. 10This counts API token cost only. It does not include cache-write charges, retries, embeddings, batch discounts or anything you spend outside the model API.

Want the full breakdown by route?

We can send you a written report that takes this estimate apart: which model tiers you could drop to, what prompt caching would actually save you, and where the same spend usually hides in a codebase like yours. Leaving an email is entirely optional. The calculator above is complete without it and nothing on this page is hidden behind a form.

We store your address and the figures above so we can write the report. Nothing else, and no third-party trackers. See the privacy page.

How this actually gets billed

The gap between Pro and Flash is the largest single-provider gap on this page. Flash prices input at a small fraction of Pro, which means a workload split across both can cost less than a tenth of the same workload run entirely on Pro.

Long context is where Gemini bills differently from the others. The published rate applies up to a context threshold, above which it changes, so a retrieval pipeline that grew its context window quietly changed its own unit economics.

Flash-Lite exists for the routes that are really classification wearing a chat interface. If a route's output is one of five fixed answers, it almost certainly does not need Pro.

If you would rather not guess at token counts, upload a usage export on the free analysis page and we will work from your real numbers. Or wrap one client with the SDK and see it measured, on the free tier.

Questions people ask

Which Gemini model should I start on?
Start on the one you are already running and use this page to price the alternative. The useful comparison is not Pro against Flash in the abstract, it is your traffic on both, which is what the verification step in Cost measures.
Does this include grounding or search tool charges?
No. This page prices model tokens only. Grounding, embeddings, fine-tuning and anything billed outside the model API are excluded, and the page says so under the result.

Price something else