modelbenchmark.io

Claude Fable 5.2

Anthropic · claude-fable-5-2-default

Compare

Claude model for demanding reasoning and long-horizon agentic work

Specification

most-agreed values

Context
1M
Max output
128K
Released
2026-11-09
Knowledge cutoff
2026-06
Retires
2027-11-09
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$8.00
Output
$40.00
Cache read
$0.20
Cache write
$10.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputvertex_ai-anthropic_models$4.00
Batch outputvertex_ai-anthropic_models$20.00
Cache write, 1 hourvertex_ai-anthropic_models$16.00

Batch input is 50% below the interactive input price at the same listing.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
google-vertex$8.00$40.00$0.20$10.001M128K—
google-vertex-anthropic$8.00$40.00$0.20$10.001M128K—
vertex_ai-anthropic_models$8.00$40.00$0.20$10.001M128K2027-11-09

Other listings of this model

this page is one of them

The corpus files Claude Fable 5.2 under several keys. This page is the claude-fable-5-2-default listing. The full record — every host, every price and every benchmark score — is on the main Claude Fable 5.2 page.

More from Anthropic

most-hosted first