Cost
Calculator
Enter how much a task uses and see what every major model would cost — ranked cheapest first. Size an API bill before you commit.
| Model | Provider | Cost / call | Cost / month | vs cheapest |
|---|
Not sure which model you actually need?
LogitMax teaches the AI frontier in 30 short modules — how to match a model to a job without overpaying.
Start learning →How LLM pricing works
How is the cost calculated?
(input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price). Input and output are billed separately, so a task that reads a lot but answers briefly costs very differently from one that writes long responses.
What is a token?
A fragment of text — roughly 0.75 words, or about 4 characters of English. So 1,000 tokens is about 750 words. "Words" mode above converts for you (1 word ≈ 1.33 tokens, an estimate).
Why does output cost more than input?
Generating each output token runs a full forward pass through the model — heavier than reading input — so output is often priced 3–6× the input rate. Verbose answers, not long prompts, drive the bill.
Where do these prices come from?
The same verified data behind our AI model & LLM pricing comparison, traced to each provider's official page.
Token estimates are approximate; every model uses its own tokenizer. Gemini 3.1 Pro is shown at its ≤200K rate ($2/$12) and costs more above 200K. Prices exclude batch and prompt-caching discounts. For planning, not billing.