modelbenchmark.io

Claude Opus 4.8 (Fast)

Anthropic · claude-opus-4-8-fast

Compare

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Specification

most-agreed values

Context
1M
Max output
128K
Released
2026-05-28
Knowledge cutoff
2026-01
Retires
2026-11-16
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · most-agreed

Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
github_copilot · github-copilot$10.00$50.00$1.00$12.50200K64K2026-11-16
venice$10.00$50.00$1.00$12.501M128K—
vercel$10.00$50.00$1.00$12.501M128K—

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02veniceCache read$1.20
2026-10-15veniceCache read$1.00
2026-09-02veniceCache write$15.00
2026-10-15veniceCache write$12.50
2026-09-02veniceInput$12.00
2026-10-15veniceInput$10.00
2026-09-02veniceOutput$60.00
2026-10-15veniceOutput$50.00

More from Anthropic

most-hosted first