modelbenchmark.io

Claude 3.5 Haiku

Anthropic · claude-3-5-haiku

Compare

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

Specification

most-agreed values

Context
200K
Max output
8K
Released
2025-08-26
Knowledge cutoff
2024-10
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.80
Output
$4.00
Cache read
$0.08
Cache write
$1.00

Available from 11 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
bedrock$0.80$4.00$0.08$1.00200K8K
bedrock · eu$0.80$4.00$0.08$1.00200K8K
bedrock · us$0.80$4.00$0.08$1.00200K8K
helicone$0.80$4.00$0.08$1.00200K8K
opencode$0.80$4.00$0.08$1.00200K8K
vercel_ai_gateway · vercel-ai-gateway$0.80$4.00$0.08$1.00200K8K
zenmux$0.80$4.00$0.08$1.00200K64K
replicate · replicate$1.00$5.00
vertex_ai-anthropic_models$1.00$5.00200K8K
heroku · heroku200K8K
qiniu-ai200K8K

Price history

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

DateHostField$/M
2026-09-02bedrock · euCache read$0.025
2026-09-11bedrock · euCache read$0.08
2026-09-02bedrock · euCache write$0.3125
2026-09-11bedrock · euCache write$1.00
2026-09-02bedrock · euInput$0.25
2026-09-11bedrock · euInput$0.80
2026-09-02bedrock · euOutput$1.25
2026-09-11bedrock · euOutput$4.00

Other listings of this model

same model, different key

More from Anthropic

most-hosted first