Head to head
GPT-4.1 vs Qwen3.8 2.4T-A95B
On a blended workload of one million input tokens and three million output tokens, Qwen3.8 2.4T-A95B is 1.2× cheaper than GPT-4.1.
| GPT-4.1 | Qwen3.8 2.4T-A95B | |
|---|---|---|
| Provider | OpenAI | Together AI |
| Input / MTok | $2 | $2.5 |
| Output / MTok | $8 | $6.25 |
| Cache read / MTok | $0.5 | — |
| Context window | 1,047,576 | — |
| Blended 1M in + 3M out | $26.00 | $21.25 |
| Status | ga | ga |