Claude Fable 5.1
Claude Fable 5.1 is an AI model developed by Anthropic that supports text, image, and file inputs. It is designed for complex agentic workflows, including long-running coding tasks and knowledge work, and features built-in reasoning and tool-calling capabilities.
Claude Fable 5.1 specs and pricing
- Provider: Anthropic
- Released: September 1, 2026
- Context window: 1M tokens
- Max output: 128K tokens
- Input: text, images, files
- Output: text
- Price: $10 input / $50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Claude Fable 5.1 is good at
- Refactoring large codebases
- Managing long-running agentic workflows
- Analyzing visual and text-based documents
To-dos to try with Claude Fable 5.1
- Read this 500-page technical manual and summarize the safety protocols for the new hardware.
- Analyze these three screenshots of a website UI and generate the corresponding HTML and CSS code.
- Review this entire repository of code and refactor the authentication module to improve security.
FAQ
- What is Claude Fable 5.1 best at? It is optimized for agentic coding, long-running agentic workflows, and complex knowledge work like long code refactors.
- Can this model process images? Yes, Claude Fable 5.1 accepts both image and file inputs in addition to standard text.
- How much does Claude Fable 5.1 cost? Claude Fable 5.1 costs $10 per million input tokens and $50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 35 credits ($1 = 100 credits).
- What is the context window of Claude Fable 5.1? Claude Fable 5.1 can read up to 1M tokens at once and write up to 128K tokens in one reply.
- Can I use Claude Fable 5.1 without coding? Yes. In todo.is you pick Claude Fable 5.1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.