AI API Cost Calculator & Model Comparison
Estimate what an LLM integration really costs: pick a model, enter input and output tokens, and see the price per call plus daily and monthly projections. Every price is editable, so you can plug in the latest list prices or your negotiated rates.
🔒 100% private — files never leave your browser
Tip: the Token Counter tells you exactly how many tokens your prompts use.
- Per request
- —
- Per day
- —
- Per month
- —
- Per year
- —
Compare model costs
| Model | Per request | Per day | Per month |
|---|
How to use the LLM API Cost Calculator
- 1 Pick a model from the list, or choose "Custom" and type your own rates.
- 2 Enter input and output tokens per request (the token counter tool tells you exactly how many).
- 3 Set your expected requests per day/month — costs update live per call, per day and per month.
Frequently asked questions
How accurate are the prices?
The built-in rates are provider list prices (per 1M tokens, USD) captured at build time and may be outdated — API pricing changes often. That is why every field is editable, and the Custom model lets you paste any current rate.
Why are output tokens more expensive?
Generating text is far more compute-intensive than reading it — output tokens typically cost 3–8× the input price. The calculator keeps them separate so estimates match how providers bill.
Does it account for prompt caching or batch discounts?
Not directly. Some providers discount cached input tokens by 50–90% and batch requests by 50%. Model those scenarios by entering an adjusted per-token rate in the Custom fields.