{"version":"2.1.314","anchor":"fable-model-alias-and-1m-context-matching-loosened","canonical_anchor":"fable-model-alias-and-1m-context-matching-loosened","heading":"The fable model aliases resolve in more cases","tier":"notice","area":"Models","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.314\/e\/fable-model-alias-and-1m-context-matching-loosened","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.314","markdown":"### The fable model aliases resolve in more cases\n\nThe `fable` and `fable[1m]` aliases now map to a model in more cases, and the 1M-context check adds an extra model-family test\n\n**What**\n\nAn alias is a short name you can type instead of a full model name. The `fable` and `fable[1m]` aliases used to resolve only when the model's family was fable. They now resolve to the mapped model in more cases. The check for whether a model gets a 1-million-token context window now also returns no when the model fails an extra family test.\n\n**Why**\n\nThis affects how custom or third-party model names are treated when they are used as fable.\n\n- Area: Models\n- Names: `fable`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no"}