modelbenchmark.io

Qwen3-Coder 480B-A35B Instruct

Alibaba · qwen3-coder-480b-a35b-instruct-int4-mixed-ar

Compare

Open Qwen coding heavyweight for repository reasoning and agentic engineering

Specification

most-agreed values

Context
106K
Max output
11K
Released
2026-04-30
Knowledge cutoff
2025-04
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.445
Output
$2.145
Cache read
$0.2225
Cache write
$0.44

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
io-net · intel$0.22$0.95$0.11$0.44106K4K
hyper$0.445$2.145$0.2225106K11K

Other listings of this model

this page is one of them

The corpus files Qwen3-Coder 480B-A35B Instruct under several keys. This page is the qwen3-coder-480b-a35b-instruct-int4-mixed-ar listing. The full record — every host, every price and every benchmark score — is on the main Qwen3-Coder 480B-A35B Instruct page.

More from Alibaba

most-hosted first