Models Model details

Anthropic

Anthropic: Claude Fable 5.1

anthropic/claude-fable-5.1

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.

Input
$10

/ 1M tokens

Output
$50

/ 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

Sep 1, 2026

Reasoning

RequiredDefault HighMaxXhighHighMediumLow

Publication status

Hugging Face: not mappedLicense: not publishedParameter count: not published

Modalities

Input · TextInput · ImageInput · FileOutput · Text

Generation controls

Include reasoningMax completion tokensMax tokensReasoningReasoning effortResponse formatStopStructured outputsTool choiceToolsVerbosity

Capability scores

57.9
Agentic index

Better than 98% of models compared

81.6
Coding index

Better than 98% of models compared

53.4
Intelligence index

Better than 97% of models compared

Agent tasks

Category performance

Slide decks
Top 3%

1328 Elo

62.6% win

Godot games
Top 2%

1327 Elo

60.7% win

Full-stack apps
Top 2%

1326 Elo

57.2% win

Mobile apps
Top 8%

1265 Elo

56.3% win

Web apps
Top 2%

1309 Elo

56.1% win

Creative tasks

Category performance

3D
Top 6%

1393 Elo

67.7% win

Games
Top 4%

1384 Elo

65.6% win

ASCII art
Top 6%

1325 Elo

65.0% win

Data visualization
Top 7%

1344 Elo

61.8% win

UI components
Top 7%

1338 Elo

59.6% win

Code
Top 7%

1338 Elo

59.3% win

SVG
Top 8%

1301 Elo

56.4% win

Websites
Top 8%

1314 Elo

56.3% win