modelbenchmark.io

Qwen/Qwen2.5-72B-Instruct

Alibaba · qwen2-5-72b-instruct

Compare

Qwen instruction model for multilingual chat, reasoning, and tool use

Specification

most-agreed values

Context
33K
Max output
4K
Released
2024-09-18
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.6172
Output
$0.6172

Available from 8 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abacus$0.11$0.38——128K8K—
hyperbolic$0.12$0.30——131K131K—
nebius$0.13$0.40——128K128K—
deepinfra$0.36$0.40——33K33K—
siliconflow$0.59$0.59——33K4K—
siliconflow-cn$0.6172$0.6172——33K4K—
fireworks_ai$0.90$0.90——33K33K—
together_ai$1.20$1.20——33K33K—

Price history

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

DateHostField$/M
2026-09-02siliconflow-cnInput$0.59
2026-10-22siliconflow-cnInput$0.6172
2026-09-02siliconflow-cnOutput$0.59
2026-10-22siliconflow-cnOutput$0.6172

More from Alibaba

most-hosted first