Claude Fable 5
Anthropic's most capable widely released model — adaptive thinking always on, for the most demanding reasoning and long-horizon agentic work
Quick calculator
Tips to reduce cost
- →Use prompt caching to reuse repeated system prompts
- →Trim whitespace and reduce verbose instructions
- →Use a smaller model for classification or routing tasks
- →Batch async requests to get 50% discount (OpenAI/Anthropic)
- →Cache identical requests at the application layer
Similar models from Anthropic
Compared at your current token settings
About Claude Fable 5
Claude Fable 5 is a premium large language model from anthropic, priced at $10/1M input tokens and $50/1M output tokens. It is priced above the market average and best suited for frontier reasoning & agents. The 1M context window makes it suitable for very long documents, large codebases, and book-length inputs.
For most production workloads, the cost breakdown is dominated by input tokens (system prompts, context, retrieved documents) rather than output. At this price point, Claude Fable 5 is positioned for use cases where quality justifies the premium over cheaper alternatives.
Claude Fable 5 supports prompt caching at $1/1M — a 90% discount on repeated input tokens. For applications with a fixed system prompt or repeated document context (RAG, chatbots, agents), enabling caching is the single highest-leverage cost optimization available.