Models Model details

Anthropic

Anthropic: Claude Sonnet 4.6

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. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Input
$3

/ 1M tokens

Output
$15

/ 1M tokens

Context window
1M

tokens

Limits

Context

1,000,000

tokens

Max output

128,000

13% of the context window

Model facts

Author

Anthropic

Tokenizer

Claude

Modality

Text + Image + File -> Text

Created

Feb 17, 2026

Reasoning

Default MediumMaxHighMediumLowNone

Publication status

Hugging Face: unavailableLicense: not publishedParameter count: not published

Modalities

Input · TextInput · ImageInput · FileOutput · Text

Generation controls

Include reasoningMax completion tokensMax tokensReasoningReasoning effortResponse formatStopStructured outputsTemperatureTool choiceToolsTop kTop pVerbosity

Capability scores

31.8
Agentic index

Better than 65% of models compared

63
Coding index

Better than 67% of models compared

30.1
Intelligence index

Better than 72% of models compared

Agent tasks

Category performance

Full-stack apps
Top 35%

1213 Elo

64.3% win

Mobile apps
Top 35%

1209 Elo

63.6% win

Android apps
Top 39%

1211 Elo

62.0% win

Godot games
Top 36%

1226 Elo

60.6% win

Web apps
Top 57%

1182 Elo

57.0% win

Agentic games
Top 71%

1177 Elo

52.2% win

Creative tasks

Category performance

ASCII art
Top 33%

1238 Elo

60.1% win

Websites
Top 20%

1286 Elo

60.0% win

Code
Top 23%

1278 Elo

59.4% win

Games
Top 33%

1260 Elo

58.8% win

SVG
Top 36%

1196 Elo

58.7% win

UI components
Top 30%

1271 Elo

58.3% win

Data visualization
Top 21%

1279 Elo

58.2% win

3D
Top 36%

1235 Elo

57.6% win