List prices
| Input | $1.1 / 1M tok | |
| Cached input | $0.275 / 1M tok | |
| Output | $4.4 / 1M tok |
Estimate your monthly cost
Based on o4-mini'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 $0.275 / 1M tokens.
Frequently asked questions
How much does o4-mini cost?
o4-mini costs $1.1 per 1 million input tokens and $4.4 per 1 million output tokens, with cached input at $0.275 per 1 million tokens. These are OpenAI's list rates.
How much does a typical o4-mini request cost?
A request with 1,500 input tokens and 500 output tokens costs about $0.0039. At 1,000 such requests a month that is roughly $3.85.
How many o4-mini tokens do I get for $10?
$10 buys roughly 9.1 million input tokens or 2.3 million output tokens at list price.
How do I track o4-mini costs per end user?
Use a metering layer. With Vevee you call track() or reserve()/commit() around each o4-mini 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 o4-mini 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 o4-mini call per end user, enforces your plan limits, and shows you per-user cost. Free tier, no card.