Qwen: Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Modalities
In / Out Price
$0.26 / $2.08 per 1M
Context
262K
Released
Feb 25, 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 |
|---|---|---|---|---|---|---|---|
 SiliconFlowfp8 | 262K | $0.26 | $2.08 | — | — | — | 100.00% |
 Alibaba | 262K | $0.26 | $2.08 | — | — | — | 96.30% |
 AtlasCloudfp8 | 262K | $0.30 | $2.40 | $0.30 | — | — | 100.00% |
 Novitabf16 | 262K | $0.40 | $3.20 | — | — | — | 100.00% |