modelbenchmark.io

Claude 4.5 Haiku

Anthropic · claude-4-5-haiku

Compare

Fast Claude model for responsive assistance, classification, and lightweight agents

Specification

most-agreed values

Context
200K
Max output
64K
Released
2025-10-16
Knowledge cutoff
2025-10
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.00
Output
$5.00
Cache read
$0.10
Cache write
$1.25

Quality

1 benchmark · 1 source

Composite
79th
percentile of 334 scored models
Rank
72 / 334
±0.10 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
one configuration only
coding62nd1/3 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
SWE-Bench verified66.6high · mini-SWE-agentSWE-bench

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
helicone$1.00$5.00$0.10$1.25200K8K
replicate · replicate$1.00$5.00
qiniu-ai200K64K

More from Anthropic

most-hosted first