Cost per token
token pricing
What a model provider charges per input and output token.
01In short
What a model provider charges per input and output token.
In productionMultiply by requests, steps and retries before you promise a business case.
02Video
slot · videoCost per token in 90 secondsadd: GUIDES['cost-per-token'].video
03Guide
slot · guide
A step-by-step guide for “Cost per token” goes here. Suggested outline:
- What it is — in one paragraph
- Why it matters in production
- How to do it — 3 to 7 steps
- Pitfalls we see in the field
04Checklist
slot · checklist
Four to eight things a team can tick before go-live.
05FAQ
slot · FAQ
The three questions clients actually ask about “Cost per token”.
06Related terms
BasicsTokenThe unit a language model reads and writes — a word fragment; in English roughly three quarters of a word on average. Pricing, speed and context limits are all counted in tokens.BusinessROIWhat you get back for what you put in.OperationsPrompt cachingReusing the processed part of a repeated prompt — long instructions, shared documents — to cut cost and latency.
Where we help · Enable