anthropic logo

Anthropic

Claude Sonnet 4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.

At a glance

Input / 1M
$3
Output / 1M
$15
Context
1M
Max output
128K
Intelligence
30.1
Released
Feb 2026
Text inputImage inputFile inputReasoningTool calling

Pricing

Claude Sonnet 4.6 API pricing

Per-token rates, plus what common tasks actually cost.

Input tokensPer 1M tokens$3
Output tokensPer 1M tokens$15
Cached input (read)Per 1M tokens$0.30
Cache writePer 1M tokens$3.75
Web searchPer request$0.01

Chat message

2K in, 500 out

$13.50

per 1,000 requests

Coding task

30K in, 4K out

$150

per 1,000 requests

Long document summary

150K in, 2K out

$480

per 1,000 requests

Benchmarks

Claude Sonnet 4.6 benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

30.1

Coding index

63

Agentic index

31.8

Specs

Context window and capabilities

What it can read, what it can write, and which API features it supports.

Context window
1M tokens
Max output
128K tokens
Input types
File, Image, Text
Output types
Text
Reasoning effort
Max, High, Medium, Low
Release date
February 17, 2026
  • Tool calling
  • Structured outputs
  • JSON mode
  • Reasoning
  • Temperature
  • Stop sequences
  • Deterministic seed
  • Verbosity control

FAQ

Frequently asked questions

How much does Claude Sonnet 4.6 cost?

Claude Sonnet 4.6 costs $3 per 1M input tokens and $15 per 1M output tokens through the API. A typical chat message costs about $13.50 per 1,000 messages.

What is the context window of Claude Sonnet 4.6?

Claude Sonnet 4.6 accepts up to 1M tokens of input and can write up to 128K tokens in a single response.

What is the best alternative to Claude Sonnet 4.6?

Claude Sonnet 5 from Anthropic is a strong alternative. It offers: 1.5x cheaper output, higher intelligence score, newer release.

Can I use Claude Sonnet 4.6 alongside other models?

Yes. Shortcut Chat sends one prompt to Claude Sonnet 4.6 and any other models you pick at the same time, so you can compare answers side by side.

anthropic logo

Try Claude Sonnet 4.6 next to every other model.

Use Claude Sonnet 4.6 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.