Claude Fable 5 vs Claude Sonnet 5

Claude Fable 5 and Claude Sonnet 5 are both current anthropic production-tier models. Claude Sonnet 5 is meaningfully cheaper at $3 / $15 per 1M. Claude Fable 5 leads on reasoning, general knowledge.

Specs side by side

Metric
Anthropic
Claude Fable 5
Anthropic
Claude Sonnet 5
Input price (per 1M)$10$3
Output price (per 1M)$50$15
Context window1M tokens1M tokens
Speed tierslowbalanced
Open weightsNoNo
EU regionYesYes
Free tierNoNo
Prompt cachingYesYes
Vision inputYesYes
Extended thinkingYesYes

When to choose each

Anthropic

Choose Claude Fable 5 if…

  • Reasoning is central to your workload
  • General knowledge is central to your workload
Anthropic

Choose Claude Sonnet 5 if…

  • Cost is a priority ($3 / $15 per 1M vs $10 / $50 per 1M)

Benchmark delta

Claude Fable 5 leads on

  • Reasoning
  • General knowledge

Claude Sonnet 5 leads on

Claude Sonnet 5 has no meaningful benchmark lead in this pair.

FAQ — Claude Fable 5 vs Claude Sonnet 5

Claude Fable 5 vs Claude Sonnet 5 — which is better?

Claude Fable 5 and Claude Sonnet 5 are both current anthropic production-tier models. Claude Sonnet 5 is meaningfully cheaper at $3 / $15 per 1M. Claude Fable 5 leads on reasoning, general knowledge. The right pick depends on your use case — see "When to choose each" above for a data-driven decision.

How does Claude Fable 5 pricing compare to Claude Sonnet 5?

Claude Fable 5 costs $10 / $50 per 1M vs Claude Sonnet 5 at $3 / $15 per 1M. Claude Sonnet 5 is cheaper on output tokens by roughly 233%. Both support prompt caching, which reduces effective cost by 80-90% on repeat system prompts.

Does Claude Fable 5 or Claude Sonnet 5 have the bigger context window?

Claude Sonnet 5 has a 1M-token context window — 1× the 1M context of Claude Fable 5. Enough for entire codebases, books, or multi-document RAG.

Is there a free tier for Claude Fable 5 or Claude Sonnet 5?

Claude Fable 5: no — No free API tier; available via Claude.ai paid plans. Claude Sonnet 5: no — Default model on Claude.ai Free/Pro web chat; API requires paid credits.

Which is better for coding — Claude Fable 5 or Claude Sonnet 5?

Claude Fable 5 leads on coding benchmarks (Claude Fable 5: 98/100, Claude Sonnet 5: 95/100). For production coding agents also weigh tool-use performance — Claude Fable 5 scores 97, Claude Sonnet 5 scores 96.