PyyanThe AI Index

Pyyan / Compare / Claude Sonnet 5 vs Claude Fable 5

Claude Sonnet 5 vs Claude Fable 5

2 of 5

Language Models · verified 13 Aug 2026

Claude Sonnet 5Anthropiccurrent
Claude Fable 5Anthropiccurrent
3 slots left
SpecificationClaude Sonnet 5Claude Fable 5
SummaryNear-Opus quality on coding and agentic work at Sonnet cost.Most capable widely released model, for the hardest reasoning and long-horizon agentic work.
Context1M1M
Input ($/Mtok)$3$10
Output ($/Mtok)$15$50
LicenceProprietaryProprietary
Max output128K128K
Model IDclaude-sonnet-5claude-fable-5
CategoryLanguage ModelsLanguage Models
OfficialAnthropic ↗Anthropic ↗

Highlighted rows are where these differ.

Claude Sonnet 5

  • Adaptive thinking on by default
  • New tokenizer — roughly 30% more tokens for the same text
  • Introductory $2/$10 through 31 Aug 2026

Best for high-volume production.

Full spec sheet →

Claude Fable 5

  • Thinking is always on — the `thinking` param is rejected
  • Raw chain of thought is never returned
  • Requires 30-day data retention; unavailable under ZDR

Best for the hardest problems.

Full spec sheet →