Back to all models
Get all the details on Claude 3.5 Sonnet, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as agent_components, batch_processing, citations, available API code samples, and performance strengths.
Key Metrics
Input Limit
200K tokens
Output Limit
4.1K tokens
Input Cost
$3.00/1M
Output Cost
$15.00/1M
Sample API Code
import anthropic
client = anthropic.Anthropic(
api_key="my api key",
)
message = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello, Claude"}
]
)
print(message.content)Required Libraries
anthropic
@anthropic-ai/sdk
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1283 | OpenLLM Leaderboard | - | |
1238 | OpenLLM Leaderboard | - | |
1183 | OpenLLM Leaderboard | - | |
57.94 | LiveBench | - | |
43.22 | LiveBench | - | |
73.90 | LiveBench | - | |
50.54 | LiveBench | - | |
56.19 | LiveBench | - | |
54.48 | LiveBench | - | |
69.30 | LiveBench | - | |
65 | Vellum LLM Leaderboard | - | |
49 | Vellum LLM Leaderboard | - | |
78 | Vellum LLM Leaderboard | - | |
56.46 | Vellum LLM Leaderboard | - | |
51.6 | Vellum LLM Leaderboard | - |
Notes
Combines top-tier performance with improved speed. Designed for enterprise use cases, focusing on security, trustworthiness, and scalability. Resistant to jailbreaks and misuse. Very low hallucination rates. Accurate over long documents. Great for coding tasks and fluency in English and non-English languages.
Capabilities
agent components
batch processing
citations
computer use
embeddings
extended thinking
function calling
long context
multilingual support
multimodal input
pdf support
prompt caching
streaming messages
token counting
tool use
vision
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
complex reasoning
advanced problem solving
sophisticated language understanding and generation
high level strategic planning
code generation
real time chatbots
data extraction and labeling
content classification
multimodal understanding
long context processing
accuracy over long documents
fluency in multiple languages
Additional Information
Latest Update
Oct 22, 2024
Knowledge Cutoff
Apr 1, 2024