List prices
| Input | $15 / 1M tok | |
| Cached input | $7.5 / 1M tok | |
| Output | $60 / 1M tok |
Estimate your monthly cost
Based on o1's current list prices. You pay your provider directly - Vevee meters this usage against your own plans.
Repeated prompts can be cheaper: cached input is $7.50 / 1M tokens.
Frequently asked questions
How much does o1 cost?
o1 costs $15 per 1 million input tokens and $60 per 1 million output tokens, with cached input at $7.5 per 1 million tokens. These are OpenAI's list rates.
How much does a typical o1 request cost?
A request with 1,500 input tokens and 500 output tokens costs about $0.052. At 1,000 such requests a month that is roughly $52.50.
How many o1 tokens do I get for $10?
$10 buys roughly 0.7 million input tokens or 0.2 million output tokens at list price.
How do I track o1 costs per end user?
Use a metering layer. With Vevee you call track() or reserve()/commit() around each o1 request with the end user's ID, define plan limits in the dashboard, and Vevee enforces them and shows per-user usage and cost - no backend to build.
Track o1 spend per user
Knowing the list price is half the problem - the other half is knowing which of your users consume it and stopping the ones who blow past their plan. Vevee meters every o1 call per end user, enforces your plan limits, and shows you per-user cost. Free tier, no card.