Estimator
See the bill before you build.
You do not need a prompt yet. Give us the use case and the scale, and you get a monthly figure. Prices and token ratios are measured; volumes and context lengths are assumptions. We separate the two on screen, and every assumption is editable.
New to these terms? 30-second primer
- Token
- The smallest unit an AI reads and writes. Roughly 1-2 tokens per English word; Korean is about 0.3-0.7 tokens per character. Billing is based on this count.
- Input / output
- Input is what you send; output is what the model writes back. Output is usually several times more expensive.
- Reasoning tokens
- What the model thinks through before answering. You never see it, but it is billed as output. This is why bills come in far above expectations.
- Context
- The maximum length of text you can send in one call.
- Cache hit
- The discount you get when the same leading portion is sent repeatedly.
What are you building?
Use case and scale are enough for a monthly figure
1 · Use case
2 · Scale
3 · Assumptions behind this estimate click to edit
—
incl. 10% Korean VAT—
%
→ Suggested sell price —
Pinned scenarios
| Scenario | Input per call | Calls per item | Items per month | Cheapest model | Monthly |
|---|
Already have a prompt? Paste it and we recalculate with real token counts. Nothing is sent to our servers.
Calculate with your own prompt
Runs entirely in your browser · nothing is sent to our servers
Estimated input tokens
The default output figure comes from the measured median for the selected job. Override it if you know your own.
Monthly cost for your workload
Want an alert when these prices change?