Head to head
GPT-OSS 120B vs Gemma 4 31B Instruct (Pearl AI)
On a blended workload of one million input tokens and three million output tokens, GPT-OSS 120B is 1.5× cheaper than Gemma 4 31B Instruct (Pearl AI).
| GPT-OSS 120B | Gemma 4 31B Instruct (Pearl AI) | |
|---|---|---|
| Provider | Together AI | Together AI |
| Input / MTok | $0.15 | $0.28 |
| Output / MTok | $0.6 | $0.86 |
| Cache read / MTok | — | — |
| Context window | 128,000 | 32,000 |
| Blended 1M in + 3M out | $1.95 | $2.86 |
| Status | ga | ga |