HASTATAgent stack guide qwen
Qwen3.8 2.4T A95B
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
Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)
Minimum context1.05M
Output256K
Providers7
CapabilitiesTool calling, Reasoning
Provider offers
| Providers | Input / 1M | Output / 1M | Cache read / 1M | Context / output | Updated |
|---|---|---|---|---|---|
 Cortecsqwen3.8-2.4t-a95b | $2.50 | $6.00 | $0.63 | 256K | 2026-08-12 |
 Deep InfraQwen/Qwen3.8-2.4T-A95B | $2.00 | $6.00 | $0.20 | 256K | 2026-08-12 |
 Hugging FaceQwen/Qwen3.8-2.4T-A95B | $2.50 | $6.25 | Unavailable | 256K | 2026-08-12 |
 OpenRouterqwen/qwen3.8-2.4t-a95b | $2.00 | $6.00 | $0.25 | 1.05M | 2026-08-12 |
 Vercel AI Gatewayalibaba/qwen3.8-2.4t-a95b | $2.00 | $6.00 | $0.20 | 256K | 2026-08-12 |
 Eden AIqwen/qwen3.8-2.4t-a95b | $2.00 | $6.00 | $0.25 | 1M | 2026-08-12 |
 Kilo Gatewayqwen/qwen3.8-2.4t-a95b | $2.00 | $6.00 | $0.25 | 1M | 2026-08-12 |
Lowest reported provider price in USD per 1M tokens; unavailable is not free. Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.
Source metadata and limitations
Capabilities are source-reported. Tool calling does not prove quality in a particular harness. Prices and limits can change.
Modalities: text → text