Claude 3.5 Sonnet
Available frontierAnthropic's most capable model for complex reasoning and code generation
Released June 20, 2024
Last tested: 2026-01-15
About
Claude 3.5 Sonnet delivers best-in-class performance on coding, analysis, and creative tasks. It features a 200K context window, computer use capabilities, and exceptional instruction following at a cost-effective price point.
Capabilities
Pricing
- Input
- $3.00/M per 1M tokens
- Output
- $15.00/M per 1M tokens
Static pricing
Details
Overview
Claude 3.5 Sonnet represents the optimal balance between capability and cost in Anthropic’s model lineup. It excels at complex reasoning tasks, code generation, and multi-step analysis while maintaining fast response times suitable for production applications.
Key Strengths
Code Generation & Analysis: Claude 3.5 Sonnet consistently outperforms competitors on coding benchmarks including HumanEval, MBPP, and real-world code review tasks. It can understand entire codebases through its 200K context window.
Computer Use: This model introduced Anthropic’s groundbreaking computer use capability, allowing it to control desktop applications, navigate websites, and automate complex workflows through visual understanding.
Instruction Following: Exceptional at following nuanced instructions, maintaining context across long conversations, and producing structured outputs in requested formats.
Use Cases
- Complex software development and code review
- Document analysis and summarization
- Research synthesis and report generation
- Automated workflow orchestration
- Multi-step reasoning and planning tasks
API Integration
import anthropic
client = anthropic.Anthropic()
message = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=1024,
messages=[
{"role": "user", "content": "Analyze this codebase for security vulnerabilities."}
]
) Other Anthropic Models
See all models- Claude Opus 4
- Anthropic's most advanced AI model for frontier intelligence
- Context
- 200K
- Speed
- N/A
- TTFT
- N/A
- Claude 3.5 Haiku
- Fast and affordable model for high-volume production workloads
- Context
- 200K
- Speed
- N/A
- TTFT
- N/A
- Claude 3 Opus
- Anthropic's most intelligent Claude 3 model for complex tasks
- Context
- 200K
- Speed
- N/A
- TTFT
- N/A
Get the signal, skip the noise.
Weekly digest of new models and provider updates across 41+ compute providers. Curated for AI builders who ship.