modelbenchmark.io

Claude Opus 5.5 (Fast)

Anthropic · claude-opus-5-5-fast

Compare

Claude model for long-running agentic coding and knowledge work

Specification

most-agreed values

Context
1M
Max output
128K
Released
2026-09-22
Knowledge cutoff
2026-06
Retires
2027-01-15
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
$0.40
Cache write
$10.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Cache write, 1 hourazure_ai$16.00

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
azure_ai$8.00$40.00$0.40$10.001M128K2027-01-15
venice$8.00$40.00$0.40$10.001M128K—
vercel$8.00$40.00$0.40$10.001M128K—

Price history

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

DateHostField$/M
2026-09-29veniceCache read$0.48
2026-10-15veniceCache read$0.40
2026-09-29veniceCache write$12.00
2026-10-15veniceCache write$10.00
2026-09-29veniceInput$9.60
2026-10-15veniceInput$8.00
2026-09-29veniceOutput$48.00
2026-10-15veniceOutput$40.00

More from Anthropic

most-hosted first