Head to head
Qwen3.5 9B vs GPT-OSS 20B
On a blended workload of one million input tokens and three million output tokens, GPT-OSS 20B is 1.4× cheaper than Qwen3.5 9B.
| Qwen3.5 9B | GPT-OSS 20B | |
|---|---|---|
| Provider | Together AI | Together AI |
| Input / MTok | $0.17 | $0.05 |
| Output / MTok | $0.25 | $0.2 |
| Cache read / MTok | — | — |
| Context window | 262,144 | 128,000 |
| Blended 1M in + 3M out | $0.92 | $0.65 |
| Status | ga | ga |