GPT-4o Mini vs GPT-5 Nano
Data reconciled August 15, 2026
Short answer
GPT-5 Nano is 3× cheaper than GPT-4o Mini on input and 1.5× cheaper on output, while giving up nothing on context or capabilities. On measurable parameters the choice is unambiguous.
Side by side
| Parameter | GPT-4o Mini | GPT-5 Nano |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input, $ per 1M tokens | $0.15 | $0.05 |
| Output, $ per 1M tokens | $0.60 | $0.40 |
| Cache read, $ per 1M | $0.075 | $0.005 |
| Context window | 128,000 | 272,000 |
| Max output | 16,384 | 128,000 |
| Vision | yes | yes |
| Tools | yes | yes |
| Reasoning | no | yes |
| Status | available | available |
What it costs on your own workload
A price gap per million tokens says little until your volumes are plugged in: on a long fixed system prompt the winner is the model with cheap cache reads, not the one with a cheap input rate. Run GPT-4o Mini and GPT-5 Nano against your own numbers.
Open the cost calculatorWhat is deliberately absent
We do not compare answer quality and we do not reprint third-party benchmarks. We have no quality measurements of our own, and external tables go stale faster than prices while being compiled, almost always, by someone with a stake in the result. What is here is only what we reconcile ourselves every day: prices, limits and supported capabilities.