modelbenchmark.io

Anthropic: Claude 3 Haiku

Anthropic · claude-3-haiku

Compare

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

Specification

anthropic listing

Context
200K
Max output
4K
Released
2024-03-07
Knowledge cutoff
2024-03
Retires
2026-04-20
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · anthropic list price

Input
$0.25
Output
$1.25
Cache read
$0.03
Cache write
$0.30

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Cache write, 1 houranthropic$0.50

Quality

3 benchmarks · 1 source

Composite
11th
percentile of 334 scored models
Rank
297 / 334
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
one configuration only
reasoning13th1/4 bench
math9th2/7 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
GPQA diamond36.3 ±2.4defaultEpoch AI2025-01-27
MATH level 514.9 ±0.7defaultEpoch AI2025-01-27
OTIS Mock AIME 2024-20251.8 ±0.8defaultEpoch AI2025-02-25

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

Available from 11 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
anthropicvendor$0.25$1.25$0.03$0.30200K4K2026-04-20
bedrock
$0.25
$0.30
$1.25
$1.50
$0.025
$0.03
$0.3125
$0.375
200K4K2026-09-10
bedrock · apac$0.25$1.25$0.025$0.3125200K4K2026-09-10
bedrock · eu$0.25$1.25$0.025$0.3125200K4K2026-09-10
bedrock · us$0.25$1.25$0.025$0.3125200K4K2026-09-10
helicone$0.25$1.25$0.03$0.30200K4K
kilo$0.25$1.25$0.03$0.30200K4K
openrouter$0.25$1.25$0.03$0.30200K4K
vercel$0.25$1.25$0.03$0.30200K4K
vercel_ai_gateway · vercel-ai-gateway$0.25$1.25$0.03$0.30200K4K
vertex_ai-anthropic_models$0.25$1.25200K4K

Other listings of this model

same model, different key

More from Anthropic

most-hosted first