modelbenchmark.io

Cogito v1 Preview Qwen 32B

cogito-v1-preview-qwen-32b

Compare

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

Specification

most-agreed values

Context
128K
Max output
33K
Released
2025-05-10
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.80
Output
$1.80
Cache read
$0.90

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
fireworks_ai$0.90$0.90131K131K
nano-gpt · deepcogito$1.80$1.80$0.90128K33K