Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
Specification
most-agreed values
Context
1M
Max output
66K
Released
2026-05-21
Knowledge cutoff
—
Retires
—
Open weights
no
Input
text, image, video
Output
text
Price
US dollars per million tokens · most-agreed
Input
$2.70
Output
$8.05
Cache read
$0.27
Cache write
$3.35
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| kyma · kyma | $2.071 | $6.207 | $0.1688 | — | 1M | 33K | — |
| venice | $2.70 | $8.05 | $0.27 | $3.35 | 1M | 66K | — |
Other listings of this model
this page is one of them
The corpus files Qwen 3.7 Max under several keys. This page is the qwen-3-7-max listing. The full record — every host, every price and every benchmark score — is on the main Qwen 3.7 Max page.
More from Alibaba
most-hosted first