Back
AnthropicClaude API
Claude Fable 5 and Claude Mythos 5 use the tokenizer introduced with Claude Opus 4.7
AI summary
Written by AI from the official notes. Check them for exact details.Claude Fable 5 and Claude Mythos 5 now use a new tokenizer and include enhanced safety features.
- New tokenizer increases token count by roughly 30% for Claude Fable 5 and Mythos 5.
- Safety classifiers now run on requests, with refusals marked by
stop_reason: "refusal". - Adaptive thinking is the only mode supported in Claude Fable 5 and Mythos 5.
- Scheduled deployments are now supported in Claude Managed Agents.
- Swift package in beta allows Claude integration in Apple's Foundation Models framework.
Why it matters: Developers and users of Claude models should be aware of the new tokenizer and safety features for better prompt management.
Full release notes11 changes
- 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-infallbacksparameter (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.categoryfield 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. - On Claude Fable 5 and Claude Mythos 5, adaptive thinking is the only thinking mode:
thinking: {"type": "disabled"}is not supported, and manual extended thinking budgets and assistant prefill are not supported (both return a 400 error). See Migrating from Claude Mythos Preview to Claude Mythos 5. - On Claude Fable 5 and Claude Mythos 5,
thinking.displaydefaults to"omitted", the same as Claude Opus 4.8, Claude Opus 4.7, and Claude Mythos Preview; setdisplay: "summarized"to receive readable thinking summaries. The raw chain of thought is never returned; pass thinking blocks back unchanged in multi-turn conversations on the same model. See Thinking output on Claude Fable 5 and Claude Mythos 5. - Claude Fable 5 requires 30-day data retention and is not available under zero data retention. See Model-specific data retention requirements.
- Claude Managed Agents now supports scheduled deployments, letting you run sessions on a cron schedule without managing your own scheduler.
- Claude Managed Agents vaults now support environment variable credentials, so you can securely inject secrets into the agent's sandbox for CLIs, SDKs, and other services that authenticate through environment variables.
- The Compliance API Activity Feed (
GET /v1/compliance/activities) is now available on Claude Platform on AWS. See IAM actions for Claude Platform on AWS for theListComplianceActivitiesaction that authorizes it. - The
session.thread_*webhook events now include asession_thread_idfield identifying the multiagent thread that triggered the event. - We've released a Swift package in beta that adds Claude as a server-side
LanguageModelin Apple's Foundation Models framework. Call Claude through the sameLanguageModelSessionAPI as Apple's on-device model on iOS 27, macOS 27, visionOS 27, and watchOS 27 (beta).