Back to all models
Get all the details on Claude 3.7 Sonnet, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as advanced_reasoning, agent_capabilities, batch_processing, 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-3-7-sonnet-20250219',max_tokens=1024,messages=[{'role': 'user', 'content': 'Hello, world!'}]);print(message.content);Required Libraries
anthropic
@anthropic-ai/sdk
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1290 | lmarena.ai | - | |
1357 | lmarena.ai | - | |
1208 | lmarena.ai | - | |
64.62 | livebench.ai | - | |
49.11 | livebench.ai | - | |
74.28 | livebench.ai | - | |
64.65 | livebench.ai | - | |
59.96 | livebench.ai | - | |
63.19 | livebench.ai | - | |
76.49 | livebench.ai | - | |
62.3 | vellum.ai | - | |
23.3 | vellum.ai | - | |
68 | vellum.ai | - | |
82.2 | vellum.ai | - | |
58.3 | vellum.ai | - | |
60.4 | vellum.ai | - |
Notes
Our most intelligent model with extended thinking capabilities. Balances intelligence and speed for high-throughput tasks. 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
advanced reasoning
agent capabilities
batch processing
citations
embeddings
extended thinking
function calling
long context
multilingual support
pdf support
prompt caching
streaming
token counting
tool use
vision
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
extended thinking
complex reasoning
advanced problem solving
nuanced strategic analysis
sophisticated research
code generation
vision tasks
tool use
long context processing
low hallucination rate
accuracy over long documents
multilingual fluency
Additional Information
Latest Update
Feb 19, 2025
Knowledge Cutoff
Apr 1, 2024