Back to all models
Get all the details on Claude 3 Haiku, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as multimodal_input, multilingual, vision, available API code samples, and performance strengths.
Key Metrics
Input Limit
200K tokens
Output Limit
4.1K tokens
Input Cost
$0.25/1M
Output Cost
$1.25/1M
Sample API Code
import anthropic;client = anthropic.Anthropic(api_key="my_api_key",);message = client.messages.create(model="claude-3-haiku-20240307",max_tokens=1024,messages=[{"role": "user", "content": "Hello, Claude"}]);print(message.content)Required Libraries
anthropic
@anthropic-ai/sdk
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1176 | lmarena.ai | Rank 104 (Default) | |
1000 | lmarena.ai | Rank 50 (Default) | |
44.98 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
26.19 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
53.17 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
34.84 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
54.12 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
39.71 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
61.88 | livebench.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
41.6% | vellum.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
40.6% | vellum.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
69.4% | vellum.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
54.31% | vellum.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. | |
28% | vellum.ai | Score for Claude 3.5 Haiku, not Claude 3 Haiku. |
Notes
Fastest and most compact model for near-instant responsiveness.
Capabilities
multimodal input
multilingual
vision
prompt caching
batch processing
tool use
streaming
token counting
embeddings
pdf support
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
quick response applications
targeted performance
Good at
human like interactions
simple tasks
Additional Information
Latest Update
Mar 7, 2024
Knowledge Cutoff
Aug 1, 2023