modelbenchmark.io

Qwen3 Coder 480B A35B Instruct

Alibaba · qwen3-coder-480b-a35b-instruct-fp8

Compare

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

Specification

most-agreed values

Context
262K
Max output
262K
Released
2025-08-23
Knowledge cutoff
2025-04
Retires
2026-06-04
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.20
Output
$0.80
Cache read
free

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
submodel$0.20$0.80262K262K
tensormesh · tensormesh$0.45$1.80free262K262K
together_ai$2.00$2.00256K2026-06-04
togetherai$2.00$2.00262K262K

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-fp8 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