qwen
Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
| Provider | Model id | Context | Price | Status |
|---|---|---|---|---|
| IteraCompute | qwen/qwen3.8-2.4t-a95b | 970,000 | $1.95–$5.95 | — |
| Charm Hyper | qwen3.8-2.4t-a95b | 1,000,000 | $2–$6 | — |
| Requesty | qwen3.8-2.4T-A95B | 262,144 | $2–$6 | — |
| Eden AI | qwen/qwen3.8-2.4t-a95b | 1,000,000 | $2–$6 | — |
| Modal | Qwen/Qwen3.8-2.4T-A95B | 1,010,000 | $2–$6 | — |
| Deep Infra | Qwen/Qwen3.8-2.4T-A95B | 262,144 | $2–$6 | — |
| Kilo Gateway | qwen/qwen3.8-2.4t-a95b | 1,000,000 | $2–$6 | — |
| OpenRouter | qwen/qwen3.8-2.4t-a95b | 1,048,576 | $2–$6 | — |
| RunInfra | Inferact/Qwen3.8-2.4T-A95B-NVFP4 | 262,144 | $2–$6 | — |
| AIHubMix | qwen3.8-2.4t-a95b | 262,000 | $2–$6 | — |
| Vercel AI Gateway | alibaba/qwen3.8-2.4t-a95b | 262,144 | $2–$6 | — |
| Fireworks AI | accounts/fireworks/models/qwen3p8-2p4t-a95b | 262,144 | $2–$6 | — |
| Hugging Face | Qwen/Qwen3.8-2.4T-A95B | 262,144 | $2.5–$6.25 | — |
| Cortecs | qwen3.8-2.4t-a95b | 262,144 | $2.5–$6 | — |
| TensorX | qwen/qwen3.8-2.4t-a95b | 262,144 | $2.5–$6 | — |
| Venice AI | qwen-3-8-2-4t-a95b | 262,144 | $2.5–$7.5 | — |
| Requesty | qwen3.8-2.4T-A95B@eu | 1,000,000 | $2.5–$6 | — |
| Merge Gateway | qwen/qwen3.8-2.4t-a95b | 262,144 | $2.5–$6.25 | — |