GPT-5 Mini vs Mistral Large 3
Data reconciled August 15, 2026
Short answer
GPT-5 Mini and Mistral Large 3 each win on different axes — neither is simply cheaper or better across the board.
GPT-5 Mini is 2× cheaper on input.
Mistral Large 3 is 1.3× cheaper on output.
GPT-5 Mini holds a 1× larger context window.
Mistral Large 3 returns a 2× longer answer per call.
Reasoning mode is supported only by GPT-5 Mini.
Side by side
| Parameter | GPT-5 Mini | Mistral Large 3 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Input, $ per 1M tokens | $0.25 | $0.50 |
| Output, $ per 1M tokens | $2.00 | $1.50 |
| Cache read, $ per 1M | $0.025 | — |
| Context window | 272,000 | 262,144 |
| Max output | 128,000 | 262,144 |
| Vision | yes | yes |
| Tools | yes | yes |
| Reasoning | yes | no |
| 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-5 Mini and Mistral Large 3 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.