Head to head
GPT-OSS 120B vs Gemini 2.5 Flash-Lite
On a blended workload of one million input tokens and three million output tokens, Gemini 2.5 Flash-Lite is 1.5× cheaper than GPT-OSS 120B.
| GPT-OSS 120B | Gemini 2.5 Flash-Lite | |
|---|---|---|
| Provider | Together AI | |
| Input / MTok | $0.15 | $0.1 |
| Output / MTok | $0.6 | $0.4 |
| Cache read / MTok | — | $0.01 |
| Context window | 128,000 | — |
| Blended 1M in + 3M out | $1.95 | $1.30 |
| Status | ga | ga |