modelbenchmark.io

claude-sonnet-4-6-thinking

Anthropic · claude-sonnet-4-6-thinking

Compare

Claude workhorse for coding agents, careful analysis, and production cost control

Specification

most-agreed values

Context
1M
Max output
64K
Released
2026-02-17
Knowledge cutoff
2025-08-31
Retires
—
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$3.00
Output
$15.00
Cache read
$0.30
Cache write
$3.75

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
302ai$3.00$15.00$0.30$3.751M64K—

Other listings of this model

this page is one of them

The corpus files claude-sonnet-4-6-thinking under several keys. This page is the claude-sonnet-4-6-thinking listing. The full record — every host, every price and every benchmark score — is on the main claude-sonnet-4-6-thinking page.

More from Anthropic

most-hosted first