Claude Code v2.1.170 Major Update - Now offering Mythos Class 1 Model Claude Fable 5!
This page has been translated by machine translation. View original
This is Ishikawa from the Cloud Business Division. Claude Code v2.1.170 was released on June 9, 2026. The biggest topic this time is support for the new model Claude Fable 5. A bug fix for session transcripts not being saved is also included.
Update Summary
v2.1.170 includes 2 changes. The highlight is that the new model Claude Fable 5 is now available from Claude Code, and the other change is a bug fix for sessions not being recorded when launched from the VS Code integrated terminal or similar environments.
Notable Updates
- New feature: Support for the new model Claude Fable 5 (Mythos class) has been added. It will be available after updating to v2.1.170.
- Bug fix: A bug where session transcripts were not saved and did not appear in
--resumewhen launched from the VS Code integrated terminal or similar environments has been fixed.
Update Details
New Feature: Support for Claude Fable 5
In v2.1.170, Claude Fable 5 is now available from Claude Code. The CHANGELOG describes it as "a safety-tuned version of the Mythos class model for general availability," and it becomes available by updating to v2.1.170.
Note that this change means Fable 5 has "become selectable," and does not mean the default model has been replaced with Fable 5.
Relationship Between Mythos Class, Fable 5, and Mythos 5
According to Anthropic's announcement, the relationship between the terms is as follows.
- Mythos class: A group of models positioned as a capability tier surpassing Opus. It was previously released in April 2026 as "Claude Mythos Preview."
- Claude Fable 5: A model that incorporates safety measures for general use into the Mythos class. This is the model that is now available from Claude Code.
- Claude Mythos 5: A separately offered model with fewer restrictions. It is limited to cybersecurity partners (Project Glasswing) and a future program for biological researchers, and is not intended for regular use by general Claude Code users.
The following sections focus on Fable 5, which is available from Claude Code.
Key Capabilities
Anthropic describes Fable 5 as having "capabilities surpassing any model we have previously made generally available" and "state-of-the-art (SOTA) performance on nearly all benchmarks." The areas most relevant to Claude Code use cases are as follows.
-
Software engineering: Reported to have high aptitude for complex migrations and refactoring. Stripe reported that a migration of a 50-million-line Ruby codebase, which was previously estimated to take about 2 months of manual work, was shortened to 1 day.
-
Vision (image processing): Described as state-of-the-art for tasks involving images, with the ability to reconstruct web apps from screenshots and read numerical values from scientific charts.
-
Long context: Reported to be able to maintain focus even at scales of millions of tokens. This is a characteristic that is effective for long-running agentic tasks and large codebase investigations.
These are based on official announcements and partner reports, and actual effectiveness will vary depending on the target task. It is realistic to think of this as a possibility that cross-file investigations and long-running tasks like those in Claude Code may become easier to progress with fewer interactions.
CTO Luke Anderson commented that "Fable 5 achieves advanced engineering in fewer turns than previous models and handles the complex multi-agent workflows that employees run daily with Claude Code."
Model ID and Pricing
- API identifier:
claude-fable-5 - Pricing: $10 per 1 million input tokens, $50 per 1 million output tokens
※ Rate limits are reached approximately twice as fast as with Opus.
Since Claude Code often handles long contexts, rather than using it constantly, you may want to reserve it for high-difficulty migrations and refactoring tasks.
Availability Conditions and Safety Mechanisms (Notes for Use)
These are points to be aware of before using it in practice. All are based on Anthropic's announcements.
- Availability conditions: Available via API and pay-as-you-go Enterprise. For subscription plans, it is included until June 22, 2026, and usage credits will be required from June 23, 2026 onward. Note that availability and billing methods vary depending on your contract type.
- Automatic routing of sensitive queries: Requests related to cybersecurity (offensive tasks), biology/chemistry, and model distillation attempts are detected by a classifier and automatically routed to Claude Opus 4.8. This is said to trigger in less than 5% of all sessions. It is good to understand that the model responding may change for some requests.
- Data retention: Mythos class models have a 30-day data retention period set for safety monitoring. When handling highly confidential code or using Enterprise, we recommend checking the relationship with your existing usage policies and internal regulations.
Fixes
- Fixed transcript not being saved in VS Code integrated terminal and similar environments: A bug where session transcripts were not saved and did not appear in the
--resumelist when launched from the VS Code integrated terminal or a shell that inherited Claude Code's environment variables has been fixed. This is an unobtrusive but important fix for those who use--resumeto resume past sessions.
Closing
In v2.1.170, the new model Claude Fable 5 is now available from Claude Code. While it is reported to have high aptitude for complex migrations, refactoring, and long-running agentic tasks, it is also worth keeping in mind the practical prerequisites such as pricing, availability conditions, and automatic routing of sensitive queries. Additionally, the bug where sessions were not recorded in the VS Code integrated terminal and similar environments has also been resolved. Why not update and give it a try?
Recent Updates
References