Claude 3.5 Sonnet

About Claude 3.5 Sonnet

New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at: - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems) #multimodal

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Anthropic Model Lineup

Compare all models from Anthropic to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

GPT Chat Latest

OpenAI

Input: $5.00

Output: $30.00

Context: 400k

GPT-5.6 Sol Pro

OpenAI

Input: $5.00

Output: $30.00

Context: 1.1M

GPT-5.6 Sol

OpenAI

Input: $5.00

Output: $30.00

Context: 1.1M

Fugu Ultra

Sakana

Input: $5.00

Output: $30.00

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Anthropic)

Cross Brand

🚀 Quick Start

Get started with Claude 3.5 Sonnet API

import anthropic

client = anthropic.Anthropic()

message = client.messages.create(
    model="anthropic/claude-3.5-sonnet",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(message.content[0].text)

Continue Your Decision