Head to head
GPT-4o mini vs GPT-OSS 120B
On a blended workload of one million input tokens and three million output tokens, GPT-OSS 120B is line-ball with GPT-4o mini.
| GPT-4o mini | GPT-OSS 120B | |
|---|---|---|
| Provider | OpenAI | Together AI |
| Input / MTok | $0.15 | $0.15 |
| Output / MTok | $0.6 | $0.6 |
| Cache read / MTok | $0.075 | — |
| Context window | 128,000 | 128,000 |
| Blended 1M in + 3M out | $1.95 | $1.95 |
| Status | ga | ga |