Head to head
Qwen3.8 2.4T-A95B vs Claude Haiku 4.5
On a blended workload of one million input tokens and three million output tokens, Claude Haiku 4.5 is 1.3× cheaper than Qwen3.8 2.4T-A95B.
| Qwen3.8 2.4T-A95B | Claude Haiku 4.5 | |
|---|---|---|
| Provider | Together AI | Anthropic |
| Input / MTok | $2.5 | $1 |
| Output / MTok | $6.25 | $5 |
| Cache read / MTok | — | $0.1 |
| Context window | — | 200,000 |
| Blended 1M in + 3M out | $21.25 | $16.00 |
| Status | ga | ga |