{"version":"2.1.283","anchor":"sonnet-1m-alias-detection-broadened","canonical_anchor":"sonnet-1m-alias-detection-broadened","heading":"More Sonnet 1M-context model names are recognised","tier":"notice","area":"Models","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283\/e\/sonnet-1m-alias-detection-broadened","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.283","markdown":"### More Sonnet 1M-context model names are recognised\n\nAny model name containing both \"sonnet\" and \"[1m]\" now counts as a Sonnet 1M-context name, apart from some exclusions\n\n**Unclear.** It is not clear what this check controls or which names are excluded.\n\n**What**\n\nA \"[1m]\" suffix on a model name asks for a context window of about a million tokens. The context window is how much text the model can take in at once. Claude Code now treats any model name that contains both \"sonnet\" and \"[1m]\" as a Sonnet 1M-context name, apart from a set of excluded names. Before, it matched only sonnet[1m], sonnet-4-6[1m] and sonnet-5[1m].\n\n**Why**\n\nOther Sonnet names ending in [1m] now go through the same availability check as the ones matched before.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5"}