{"version":"2.1.293","anchor":"long-prompt-pricing-tier-selection-by-prompt-tokens","canonical_anchor":"long-prompt-pricing-tier-selection-by-prompt-tokens","heading":"Model pricing gains a long-prompt tier","tier":"notice","area":"Cost Tracking","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293\/e\/long-prompt-pricing-tier-selection-by-prompt-tokens","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293","markdown":"### Model pricing gains a long-prompt tier\n\nModels can now carry a higher price for prompts over a token threshold, used in cost accounting and shown in the pricing line\n\n**Unclear.** It is not stated where Claude Code shows or uses this pricing, so it is unclear which cost figures you see would change.\n\n**What**\n\nModel pricing can now include a separate price for long prompts, used once a request's prompt passes a set number of tokens.\n\n- The baked-in model catalog reads a new `long_prompt` pricing field, keyed by `above_prompt_tokens`, next to input, output, cache and `web_search` rates. The catalog version went from 1697 to 1760.\n\n- When input, cache-read and cache-creation tokens together exceed `abovePromptTokens`, the `longPrompt` rates are used instead of the base rates.\n\n- Per-model usage records add a `longPrompt` part holding the threshold and the costs worked out at that tier.\n\n- The pricing line shows \"in\/out per Mtok\" (per million tokens) and, when a long-prompt tier exists, adds \"for prompts over N\".\n\n**Why**\n\nCost figures for very long requests can now reflect the higher rate some models charge above a prompt size, and you can see where that threshold sits.\n\n- Area: Cost Tracking\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no"}