Logo
Back to all models

Claude 3.5 Haiku - In-Depth Overview

Anthropic · Claude 3.5

Current
Latest in family

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

Get all the details on Claude 3.5 Haiku, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as long_context, prompt_caching, streaming, 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

from anthropic import Anthropic

client = Anthropic()

message = client.messages.create(
    model="claude-3-5-haiku-20241022",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Claude!"}
    ]
)
print(message.content)

Required Libraries

anthropic
@anthropic-ai/sdk

Benchmarks

BenchmarkScoreSourceNotes
1234
lmarena.ai-
1133
lmarena.ai-
1234
lmarena.ai-
44.98
livebench.ai-
26.19
livebench.ai-
53.17
livebench.ai-
34.84
livebench.ai-
54.12
livebench.ai-
39.71
livebench.ai-
61.88
livebench.ai-
41.6%
vellum.ai-
40.6%
vellum.ai-
69.4%
vellum.ai-
54.31%
vellum.ai-
28%
vellum.ai-

Notes

Our fastest model, offering quick and accurate targeted performance.

Supported Data Types

Input Types

text
image

Output Types

text

Strengths & Weaknesses

Exceptional at

speed

Good at

quick and accurate targeted performance

Poor at

extended thinking

Additional Information

Latest Update

Oct 22, 2024

Knowledge Cutoff

Jul 1, 2024