Claude Haiku 3.5 - In-Depth Overview

Anthropic · Claude

Current

Latest in family

Model ID: claude-3-5-haiku-latest

Get all the details on Claude Haiku 3.5, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as streaming, batch_processing, tool_use, available API code samples, and performance strengths.

Key Metrics

Input Limit

200K tokens

Output Limit

8.2K tokens

Input Cost

$0.80/1M

Output Cost

$4.00/1M

Sample API Code

import anthropic;client = anthropic.Anthropic(api_key="my_api_key",);message = client.messages.create(model="claude-3-5-haiku-latest",max_tokens=1024,messages=[{"role": "user", "content": "Hello, Claude!"}]);print(message.content)

Required Libraries

anthropic

@anthropic-ai/sdk

Benchmarks

Benchmark	Score	Source	Notes
lmarena text	1234	lmarena.ai	-
lmarena webdev	1133	lmarena.ai	-
lmarena vision	1000	lmarena.ai	-
livebench global average	44.98	livebench.ai	-
livebench reasoning average	26.19	livebench.ai	-
livebench coding average	53.17	livebench.ai	-
livebench mathematics average	34.84	livebench.ai	-
livebench data analysis average	54.12	livebench.ai	-
livebench language average	39.71	livebench.ai	-
livebench if average	61.88	livebench.ai	-
gpqa	41.6%	vellum.ai	-
swe bench	40.6%	vellum.ai	-
math 500	69.4%	vellum.ai	-
bfcl	54.31%	vellum.ai	-
alder polyglot	28%	vellum.ai	-

Notes

Claude 3.5 Haiku is Anthropic's fastest model, offering intelligence at blazing speeds. Models with the same snapshot date are identical across all platforms and do not change, ensuring consistent performance. Aliases are subject to the same rate limits and pricing as the underlying model version they reference.