Qwen: Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...
Modalities
In / Out Price
$2 / $6 per 1M
Context
1M
Released
Aug 12, 2026
Knowledge Cutoff
—
Providers
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
 Novita | 1M | $2 | $6 | $0.25 | — | — | 100.00% |
 Alibaba | 1M | $2 | $6 | $0.25 | — | — | 100.00% |
 SiliconFlowfp8 | 1M | $2 | $6 | $0.25 | — | — | 100.00% |
 Venice | 262K | $2 | $6 | $0.25 | — | — | — |
 Modal | 1M | $2 | $6 | $0.25 | — | — | 100.00% |
 DeepInfrafp4 | 262K | $2 | $6 | $0.20 | — | — | 100.00% |
 Together | 1M | $2 | $6 | $0.25 | — | — | 100.00% |