Model
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
1 providersreleased Aug 12, 2026open weights
$2
best input /M · Vercel AI Gateway
$6
best output /M
262K
context window
131K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Vercel AI Gateway alibaba/qwen3.8-2.4t-a95b | $2 | $6 | $0.2 | — | 262K | reasoningtoolsstructuredno vision | Aug 12, 2026 |
Price badge
https://models.sutraworks.ai/badge/alibaba/qwen3.8-2.4t-a95b.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Weights
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.