Anthropic's Claude model for demanding reasoning and long-horizon agentic work, released as the successor to Fable 5. Claude Fable 5.2 replaces it and costs less on every rate.
pick it if
your integration is pinned to 5.1 while you test Fable 5.2
you run long agent sessions; cache hits bill at 2.5% of input
skip it if
you are starting new work; Claude Fable 5.2 costs less on every rate at the same window
your code forces tool use, prefills replies or sets temperature; all return errors
Claude Fable 5 was Anthropic's generally available Fable model, released June 2026 with always-on adaptive thinking and text plus image input. Anthropic now lists it as legacy, and Claude Fable 5.1 replaced it at the same $10 / $50 price.
pick it if
you wanted Anthropic's Fable tier, adaptive thinking always on at high effort
you reused long prompts: cache reads billed at a tenth of input
you needed long answers, up to 128K output tokens per response
skip it if
you are choosing today; Fable 5.1 costs the same with cheaper cache reads
price matters more: Opus 5.5 lists at $4 / $20 on a 1M window
faq
which is cheaper, Claude Fable 5.1 or Claude Fable 5?
Claude Fable 5.1 and Claude Fable 5 list the same input and output prices. on a coding-agent session (2M tokens in, 60,000 out) Claude Fable 5.1 costs $23.00 and Claude Fable 5 $23.00.
try either model
switch between models inside the same octomind session.