modelbenchmark.io

Qwen3 30B A3B Thinking 2507

Alibaba · qwen3-30b-a3b-thinking

Compare

Qwen reasoning model for deliberate problem solving, math, and coding

Specification

most-agreed values

Context
262K
Max output
131K
Released
2025-07-31
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.36
Output
$1.30

Available from 4 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
modelscopefreefree——262K33K—
qiniu-ai$0.1087$1.087——126K32K—
clarifai$0.36$1.30——262K131K—
fireworks_ai$0.90$0.90——262K262K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02openrouterInput$0.20
2026-09-06openrouterInput$0.20
2026-09-02openrouterOutput$2.40
2026-09-06openrouterOutput$2.40

More from Alibaba

most-hosted first