Reference · Glossary

Cost per token

How providers **price API usage** — separate rates for input tokens (your prompt) and output tokens (the model's reply).

When to use

Estimating monthly bills, comparing models, deciding when to cache or compress prompts.

When not to

Local/open-weight models on your own GPU — you pay for hardware and electricity instead.

Example

$0.15 / 1M input tokens + $0.60 / 1M output tokens → a 2K-in / 500-out chat ≈ $0.0006 per turn.