AI model comparison

Claude Opus 5 vs Claude Sonnet 5

Side by side comparison of Claude Opus 5 and Claude Sonnet 5 on pricing, benchmark scores, context window, and more.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work.

Input / 1M: $5
Output / 1M: $25
Context: 1M

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.

Input / 1M: $2
Output / 1M: $10
Context: 1M

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

Claude Sonnet 5

2.5x cheaper for a typical chat

Higher intelligence score

Not available

Not enough benchmark data

Larger context window

Tie

1M vs 1M tokens

Newer release

Claude Opus 5

Released July 24, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

Claude Opus 5Not available

Claude Sonnet 5Not available

Coding index

Claude Opus 578

Claude Sonnet 571.5

Agentic index

Claude Opus 556.5

Claude Sonnet 543.6

Pricing

Claude Opus 5 vs Claude Sonnet 5 API pricing

Per-token API rates. Cheaper option highlighted.

Metric	Claude Opus 5	Claude Sonnet 5
Input tokensPer 1M tokens	$5	$2
Output tokensPer 1M tokens	$25	$10
Cached input (read)Per 1M tokens	$0.50	$0.20
Cache writePer 1M tokens	$6.25	$2.50
Web searchPer request	$0.01	$0.01

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

Claude Opus 5$22.50

Claude Sonnet 5$9

Coding task

30K in, 4K out

Claude Opus 5$250$115 cached

Claude Sonnet 5$100$46 cached

Long document summary

150K in, 2K out

Claude Opus 5$800$125 cached

Claude Sonnet 5$320$50 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metric	Claude Opus 5	Claude Sonnet 5
Context window	1M tokens	1M tokens
Max output	128K tokens	128K tokens
Input types	File, Image, Text	File, Image, Text
Output types	Text	Text
Reasoning effort levels	Max, Extra high, High, Medium, Low, None	Max, Extra high, High, Medium, Low, None
Default reasoning effort	High	High
Release date	July 24, 2026	June 30, 2026

Features

Supported features

API features available for each model.

Metric	Claude Opus 5	Claude Sonnet 5
Tool calling	Supported	Supported
Structured outputs	Supported	Supported
JSON mode	Supported	Supported
Reasoning	Supported	Supported
Temperature	Not supported	Not supported
Stop sequences	Supported	Supported
Deterministic seed	Not supported	Not supported
Verbosity control	Supported	Supported

Our take

Claude Sonnet 5 is 2.5x cheaper for a typical chat. The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Claude Opus 5 or Claude Sonnet 5 cheaper?

Claude Sonnet 5 is cheaper for a typical chat (2K input tokens and 500 output tokens). Claude Sonnet 5 costs $2 per 1M input tokens and $10 per 1M output tokens, while Claude Opus 5 costs $5 per 1M input tokens and $25 per 1M output tokens.

Which has a bigger context window, Claude Opus 5 or Claude Sonnet 5?

Claude Opus 5 supports up to 1M tokens of context, compared with 1M for Claude Sonnet 5.

Can I use Claude Opus 5 and Claude Sonnet 5 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Claude Opus 5 and Claude Sonnet 5 answer side by side and keep the better response.

Why choose? Ask both.

Send one prompt to Claude Opus 5 and Claude Sonnet 5 at the same time. Compare the answers side by side and keep the best one.

Get started See a preview