Claude Sonnet 4 - In-Depth Overview

Anthropic · Claude

Current

Latest in family

Model ID: claude-sonnet-4-0

Get all the details on Claude Sonnet 4, an AI model from Anthropic. This page covers its token limits, pricing structure, key capabilities such as long_context, multilingual_support, vision, available API code samples, and performance strengths.

Key Metrics

Input Limit

200K tokens

Output Limit

64K tokens

Input Cost

$3.00/1M

Output Cost

$15.00/1M

Sample API Code

import anthropic;client = anthropic.Anthropic(api_key="YOUR_ANTHROPIC_API_KEY",);message = client.messages.create(model="claude-sonnet-4-0",max_tokens=1024,messages=[{"role": "user", "content": "Hello, Claude!"}]);print(message.content)

Required Libraries

anthropic

@anthropic-ai/sdk

Benchmarks

Benchmark	Score	Source	Notes
livebench global average	69.65	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench reasoning average	54.86	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench coding average	77.54	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench mathematics average	76.39	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench data analysis average	64.68	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench language average	67.18	LiveBench Leaderboard	LiveBench-2025-04-25 version
livebench if average	77.25	LiveBench Leaderboard	LiveBench-2025-04-25 version

Notes

High-performance model with exceptional reasoning capabilities. Offers a 200k context window. Supports text and image input, and text output. Aliases are available for convenience but specific versions are recommended for production. Excels in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing. Supports prompt caching, extended thinking, streaming messages, and batch processing.