// AI Platform Drift

Claude Fable 5 tokenizer produces 30% more tokens than pre-Opus 4.7 models

Claude Platform release notes · published 2026-09-25 15:41 UTC
WORTH KNOWING BUDGET MODELPRICINGLIMITS
WHAT CHANGEDClaude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7. The same text produces roughly 30% more tokens compared to models before Claude Opus 4.7. Requests refused by safety classifiers before output generation are not billed. A new stop_details.category value "reasoning_extraction" is returned when requests are blocked for reverse engineering attempts.
WHY IT MATTERSYour token counts will increase by approximately 30% for the same prompts, directly increasing API costs per request. Existing token budgets, rate limit calculations, and cost forecasts based on pre-Opus 4.7 models are now inaccurate for Fable 5 and Mythos 5.
WHAT TO DORun your production prompts through the token counting API with model: "claude-fable-5" to measure actual token usage. Update cost forecasts and rate limit configurations to account for the 30% increase before switching to these models.
Model-reported confidence 95% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
 https://platform.claude.com/docs/en/release-notes/overview#june-9-2026
 Tue, 09 Jun 2026 00:00:00 GMT
 
-We've launched Claude Fable 5 (claude-fable-5), our most capable widely released model, alongside Claude Mythos 5 (claude-mythos-5) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability.
+We've launched Claude Fable 5 (claude-fable-5), our most capable model open to all customers, alongside Claude Mythos 5 (claude-mythos-5) for Project Glasswing participants. Both models support a 1M token context window by default, 128k max output tokens, and always-on adaptive thinking. See Introducing Claude Fable 5 and Claude Mythos 5 for capabilities, API changes, and availability.
 Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7. Compared to models before Claude Opus 4.7, the same text produces roughly 30% more tokens. The exact increase depends on the content and workload shape. Use the token counting API with model: "claude-fable-5" to measure your prompts under the new tokenizer.
 Claude Fable 5 runs safety classifiers on requests and during response generation. When a classifier declines a request, the Messages API returns stop_reason: "refusal". You are not billed for a request refused before any output is generated. An opt-in fallbacks parameter (in beta on the Claude API and Claude Platform on AWS; not supported on the Message Batches API) re-runs refused requests on another model, billed at the fallback model's rates. See Handling stop reasons.
 The stop_details.category field on refusal responses now includes "reasoning_extraction" on Claude Fable 5, returned when a request is blocked under Anthropic's Terms of Service restrictions on reverse engineering or duplicating model outputs. The existing "cyber" and "bio" categories are unchanged. No beta header is required.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.45
triage reasoningClaude Fable 5 availability expanded to all customers; tokenizer change affects token counting and costs; new API behaviors and fields require integration updates.
signalsmodel availability broadened · access tier changed from restricted to general · tokenizer change with quantified impact (30% more tokens) · new safety classifier behavior documented · new stop_reason value introduced · new stop_details.category value added · billing change for refused requests · new optional parameter (fallbacks) introduced
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)