Large open Qwen multimodal MoE for visual agents and long technical tasks
Specification
most-agreed values
Context
262K
Max output
262K
Released
2026-02-15
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$1.65
Output
$7.50
Cache read
$0.33
Available from 1 host
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| thinkingmachines | $1.65 | $7.50 | $0.33 | — | 262K | 262K | — |
Other listings of this model
this page is one of them
The corpus files Qwen3.5 397B-A17B under several keys. This page is the qwen3-5-397b-a17b-peft-262144 listing. The full record — every host, every price and every benchmark score — is on the main Qwen3.5 397B-A17B page.
More from Alibaba
most-hosted first