Skip to content
Convertto

LLM API Cost Calculator — GPT, Claude, Gemini

Work out what a prompt costs per call, per day and per month, and compare the same workload across every major model.

This calculator prices a language-model workload from the token counts you actually send: input, output and cached input, multiplied by a request volume. It shows the cost per call and per period, splits input against output, and ranks every major model on the identical workload so the cheapest option for your particular input-to-output ratio is visible rather than guessed.

Runs in your browser
Prices verified
2026-08-01
Models priced
25 across 7 providers
Privacy
Runs entirely in your browser — nothing is uploaded
Cost
Free, unlimited, no sign-up

Frequently asked questions

Why is output so much more expensive than input?

Input is processed in parallel in a single forward pass; output is generated one token at a time, each one requiring a full pass over the model. Output typically costs four to five times input, which is why a summarisation workload and a generation workload with the same total tokens can differ several-fold in price.

What does prompt caching actually save?

Cached input is billed at roughly a tenth of the normal input rate, but writing to the cache costs about 1.25× a normal read. With a five-minute cache you break even on the second request; with a one-hour cache you need three. It only helps when a large prefix is genuinely identical between requests.

Are reasoning tokens included?

They are billed as output even though they are not returned to you, so a reasoning model's real output count is higher than the visible response. Add your expected thinking tokens to the output figure to get a realistic number.

How current are these prices?

Every figure carries the date it was checked — currently 2026-08-01 — and links to the provider's own price list. Treat this as a planning tool, not a quotation.

How to use the ai api cost calculator

  1. 1Choose the model.
  2. 2Set the input tokens per request.
  3. 3Set the output tokens per request.
  4. 4Set the cached input tokens.
  5. 5Set the requests.
  6. 6Turn "Compare every model" on or off as needed.
  7. 7Press Run, then download the result when it is ready.

Sources & specifications

Embed this tool

Put the working ai api cost calculator on your own site. It runs in your visitors' browsers exactly as it does here — free, no account, nothing uploaded.

Share this tool

Related tools

LLM Model ComparisonEvery current model side by side: price per million tokens, context window, max output, modalities and cache rates.LLM Stream ParserPaste a raw server-sent-event stream and get the reconstructed message, tool calls, usage and stop reason.Prompt Token OptimizerStrip the padding out of a prompt — dead whitespace, boilerplate politeness, redundant framing — and see the tokens and money saved.Context Window CalculatorPaste a document and see which models it fits inside, how much of each window it fills, and what is left for the reply.LLM Token CounterCount tokens with the real BPE vocabulary, see every token coloured in place, and compare the count across models.Prompt Injection SanitizerStrip invisible carriers, neutralise instruction-like markup and fence untrusted content before you paste it into a prompt.

Last updated

More ai & llm tools