modelbenchmark.io

Qwen3 4B

Alibaba · qwen3-4b-fp8

Compare

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

Specification

most-agreed values

Context
128K
Max output
20K
Released
2025-04-29
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.03
Output
$0.03

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
novita$0.03$0.03128K8K
novita-ai$0.03$0.03128K20K

Other listings of this model

this page is one of them

The corpus files Qwen3 4B under several keys. This page is the qwen3-4b-fp8 listing. The full record — every host, every price and every benchmark score — is on the main Qwen3 4B page.

More from Alibaba

most-hosted first