modelbenchmark.io

ERNIE-4.5-21B-A3B-Thinking

Baidu · ernie-4-5-21b-a3b-thinking

Compare

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Specification

most-agreed values

Context
131K
Max output
66K
Released
2025-09-19
Knowledge cutoff
2025-03
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.07
Output
$0.28

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
helicone$0.07$0.28128K8K
novita$0.07$0.28131K66K
novita-ai · baidu$0.07$0.28131K66K

More from Baidu

most-hosted first