{"version":"2.1.287","anchor":"token-count-precheck-short-circuits-oversized-content","canonical_anchor":"token-count-precheck-short-circuits-oversized-content","heading":"Very large content skips the token-count request","tier":"internal","area":"Context","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287\/e\/token-count-precheck-short-circuits-oversized-content","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287","markdown":"### Very large content skips the token-count request\n\nWhen a local size estimate is far over a limit, Claude Code now answers its token-count check without asking the API\n\n**Unclear.** It is not clear what Claude Code uses this token-count check for.\n\n**What**\n\nBefore asking the API how many tokens (the units the model measures text in) some content uses, Claude Code makes its own rough estimate. It now compares that estimate against a second, higher limit. If the content is over that higher limit, the check answers yes straight away and the request to the API is never sent. Some parts of the content are left out of the estimate.\n\nBefore, only a lower limit was checked locally before the API request.\n\n**Why**\n\nVery large inputs no longer wait on a round trip to the API just to confirm they are too big.\n\n- Area: Context\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5"}