Head to head
GPT-5.4 mini vs o4-mini
On a blended workload of one million input tokens and three million output tokens, GPT-5.4 mini is line-ball with o4-mini.
| GPT-5.4 mini | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input / MTok | $0.75 | $1.1 |
| Output / MTok | $4.5 | $4.4 |
| Cache read / MTok | $0.075 | $0.275 |
| Context window | — | 200,000 |
| Blended 1M in + 3M out | $14.25 | $14.30 |
| Status | ga | ga |