HighPricing

Claude Fable 5 / Mythos 5 use new tokenizer: ~30% more tokens for the same text

Claude Fable 5 and Mythos 5 use the tokenizer introduced with Opus 4.7, which produces roughly 30% more tokens than earlier models for the same text, and billing reflects the higher counts. Token counts measured on older models must not be reused; the free count_tokens endpoint returns counts for the model you pass.

Action note

Before migrating any workload to Fable 5 or Mythos 5, recount your prompts via /v1/messages/count_tokens with the target model and re-budget costs and context-window fit for the ~30% token increase.

What to search in your codebase

  • Claude Fable 5 / Mythos 5 use new tokenizer: ~30% more tokens for the same text
  • Anthropic pricing

Get Anthropic change notes

One focused email when Anthropic changes need migration work or owner review.

Want Slack/webhook alerts or specific sources? Request full access