modelbenchmark.io

Anthropic: Claude 3 Haiku

Anthropic · claude-3-haiku

Compare

Legacy model retained for compatibility with older integrations

Specification

most-agreed values

Context
200K
Max output
4K
Released
2024-03-13
Knowledge cutoff
2024-03
Retires
2026-08-23
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

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

Quality

3 benchmarks · 1 source

Composite
12th
percentile of 344 scored models
Rank
303 / 344
±0.06 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
—
one configuration only
reasoning14th1/4 bench
math8th2/7 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 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
helicone$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$1.25——200K4K2026-08-23

Price history

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

DateHostField$/M
2026-09-02openrouterCache read$0.03
2026-09-19openrouterCache read$0.03
2026-09-26openrouterCache read$0.03
2026-09-02openrouterCache write$0.30
2026-09-19openrouterCache write$0.30
2026-09-26openrouterCache write$0.30
2026-09-02openrouterInput$0.25
2026-09-26openrouterInput$0.25
2026-09-02openrouterOutput$1.25
2026-09-26openrouterOutput$1.25

Other listings of this model

same model, different key

More from Anthropic

most-hosted first