> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bettertoken.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Fable 5 is live

> BetterToken updated Claude Fable 5 on June 9, 2026 for Claude Code, long-running agent tasks, complex software engineering, and intensive knowledge work.

Release date: June 9, 2026

BetterToken has updated the `Claude Fable 5` model entry. Check the <a href={"https://www.bettertoken.ai/pricing"}>model plaza</a> for the currently available model ID, then configure it through the Claude Code or external-tool setup guide that matches your client.

Anthropic officially introduced Claude Fable 5 on June 9, 2026 and describes it as a new generation of intelligence for the hardest knowledge work and coding problems. Anthropic says Fable 5 is a Mythos-class model built for longer, more complex, more asynchronous work, especially long-running agents, complex software engineering, knowledge work, and vision-heavy workflows.

## Highlights

* **Stronger long-running agent work**: Anthropic says Fable 5 can operate for longer in Claude Code or an agent harness, planning across stages, executing, and checking its own work
* **Better fit for complex software engineering**: The model is positioned for large migrations, complex implementations, multi-day autonomous sessions, and engineering tasks that need less direct supervision
* **Improved knowledge work and vision**: Fable 5 targets complex analysis, document reasoning, charts, tables, PDFs, and other visual materials
* **More active self-checking**: Anthropic emphasizes that Fable 5 validates its own work more thoroughly, which helps when you hand off a task and review the result later
* **New safeguards**: For sensitive areas such as cybersecurity, biology, and chemistry, Anthropic applies safeguards and fallback behavior; some requests may be answered by Claude Opus 4.8 instead

## Setup guidance

If you use Claude Code, start with the [Claude Code setup guide](/en/ai-tools/claude-code). Different Key groups use different protocols and model configuration patterns:

* `Claude` group: use `https://www.bettertoken.ai`
* `GPT` group or external tools: follow the relevant tool guide with `https://www.bettertoken.ai/v1`

Use the model name currently shown in the <a href={"https://www.bettertoken.ai/pricing"}>model plaza</a>. Do not hardcode a model name that is not shown there.

<Note>
  Claude Fable 5 is best for high-value, long-context, long-running tasks. For simple Q\&A or low-cost batch work, choose a lighter model based on the groups and pricing shown in the model plaza.
</Note>

## Official sources

* [Claude Fable 5 and Claude Mythos 5](https://www.anthropic.com/news/claude-fable-5-mythos-5)
* [Claude Fable 5](https://www.anthropic.com/claude/fable)