modelbenchmark.io

Qwen3 Coder 480B A35B Instruct Turbo

Alibaba · qwen3-coder-480b-a35b-instruct-turbo

Compare

Qwen coding model for software agents, repository edits, and code reasoning

Specification

most-agreed values

Context
262K
Max output
67K
Released
2025-07-22
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.30
Output
$1.00
Cache read
$0.10

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepinfra$0.30$1.00$0.10—262K
67K
262K
—
venice$0.35$1.50$0.04—256K66K—

More from Alibaba

most-hosted first