modelbenchmark.io

ERNIE 5.1 Thinking

Baidu · ernie-5-1

Compare

Compact GPT model for low-latency assistance and high-volume workloads

Specification

most-agreed values

Context
119K
Max output
64K
Released
2026-05-10
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.75
Output
$3.00
Cache read
$0.75

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.75$3.00$0.75119K64K
nano-gpt · thinking$0.75$3.00$0.75119K64K

More from Baidu

most-hosted first