Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Claude Opus 5.5 Add a modelChat with this model

Attribute	Claude Opus 5.5anthropic/claude-opus-5-5
Specs
Context window	1M
Max output	128K
Input modalities	TextImage
Output modalities	Text
Capabilities
Streaming	Supported
Tool calling	Supported
Structured output (JSON)	Supported
Image input	Supported
Thinking mode	Supported
Price / 1M tokens
Input	$ 4.00
Output	$ 20.00
Cache read	$ 0.20
Cache write	$ 5.00
What it is good at
Best for	Agentic coding Professional knowledge work Charts and screenshots
Published benchmarks
CursorBench 4.0score	57.8%effort max(setup not fully disclosed)
FrontierCode v1.1 (Main)score	54.4%effort max(setup not fully disclosed)
Terminal-Bench 4.0pass_rate	66.4%effort xhigh(setup not fully disclosed)
AutomationBenchscore	40%(setup not fully disclosed)
OSWorld 2.1 (partial credit)score	81.8%effort max(setup not fully disclosed)
GDPval-AA v2.1elo	1846effort max(setup not fully disclosed)
Chartography (with tools)score	89%effort max(setup not fully disclosed)
Humanity's Last Exam (with tools)accuracy	67.7%effort max(setup not fully disclosed)
Terminal-Bench-Science 0.1accuracy	58.7%effort max(setup not fully disclosed)