Qwen: Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
The Qwen3.5 series 397B-A17B 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. It delivers...
Modalities
In / Out Price
$0.45 / $3 per 1M
Context
262K
Released
Feb 16, 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 |
|---|---|---|---|---|---|---|---|
 Alibaba | 262K | $0.39 | $2.34 | — | — | — | 100.00% |
 DeepInfrafp8 | 262K | $0.45 | $3 | $0.22 | — | — | 100.00% |
 Parasailfp8 | 262K | $0.50 | $3.60 | $0.30 | — | — | 100.00% |
 DigitalOcean | 131K | $0.55 | $3.50 | $0.11 | — | — | 62.50% |
 Phala | 262K | $0.55 | $3.50 | $0.225 | — | — | 100.00% |
 AtlasCloudfp8 | 262K | $0.55 | $3.50 | $0.55 | — | — | 100.00% |
 StreamLake | 256K | $0.60 | $3.60 | $0.12 | — | — | 100.00% |
 GMICloudfp8 | 262K | $0.60 | $3.60 | — | — | — | 100.00% |
 Novita | 262K | $0.60 | $3.60 | — | — | — | 100.00% |
 Venice | 128K | $0.75 | $4.50 | — | — | — | 100.00% |