modelbenchmark.io

Claude Sonnet 4.5 Thinking

Anthropic · claude-sonnet-4-5-think

Compare

Balanced Claude model for coding, analysis, agent workflows, and cost control

Specification

most-agreed values

Context
200K
Max output
64K
Released
2025-09-29
Knowledge cutoff
2025-07-31
Retires
—
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.30
Output
$16.50
Cache read
$0.33
Cache write
$4.125

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
aihubmix$3.30$16.50$0.33$4.125200K64K—

More from Anthropic

most-hosted first