{"version":"2.1.242","anchor":"prompt-snippet-for-cutting-opus-5-s-time-to-first-token","canonical_anchor":"prompt-snippet-for-cutting-opus-5-s-time-to-first-token","heading":"Prompt snippet for cutting Opus 5's time to first token","tier":"notice","area":"Model Docs","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242\/e\/prompt-snippet-for-cutting-opus-5-s-time-to-first-token","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242","markdown":"### Prompt snippet for cutting Opus 5's time to first token\n\nModel guidance adds a one-line instruction to cut Opus 5's delay before its first visible output.\n\n**What**\n\nThe bundled model guidance adds a note that Opus 5 sometimes thinks before emitting its first visible block, which raises the delay before anything appears in chat and voice, along with a one-line system instruction to reduce it.\n\n**Details**\n\n- The suggested line is `Latency-sensitive; begin your visible answer immediately.`\n- The advice is to apply it only where first-token latency is visible to a person, not everywhere.\n- It also appears as a new tuning item in the Opus 5 checklist.\n\n**Evidence**\n\n`Latency-sensitive; begin your visible answer immediately.`\n\n- Area: Model Docs\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 4\/5"}