Glossary term

Context window

Glossary informational Last reviewed Updated

A context window is the maximum amount of text, measured in tokens, that a model can take into account at once when generating a response.

Mythos-class numbers

Fable 5 and Mythos 5 provide a 1M-token context window with up to 128k tokens of output. That makes them suited to long documents, large codebases, and extended multi-step sessions.

Input vs. output

The context window bounds the combined input the model reads; the separate output limit caps how much it can generate in a single response.

Sources & further reading

Facts on this page link to their source. Quotes are kept under 15 words and attributed; figures labelled unofficial are third-party until Anthropic publishes system-card numbers.