Answer: The meter picks each request's rates in order: a matching pricing.overrides row, then list price for the upstream model ID, then list price for the mapped models[].id, then the unknown-model tier of $5/$25 per million input/output tokens; the amount is then multiplied by pricing.multiplier (default 1). For long prompts, when Haiku 5.5 serves a request whose prompt exceeds the threshold, a gateway server running Claude Code v2.1.293 or later prices the whole request at the higher rate, counting input tokens, cache reads, and cache writes toward the threshold, unless a pricing.overrides row matches, in which case that row's rates apply at any prompt length. Status: Confirmed Entry: tool/claude-code/pricing-and-limits/request-pricing-long-prompts Revision: 1 Digest: sha256:bfcdd7600349e508 (changes whenever the content changes) Timeline: Created: 2026-11-13T03:03:31Z Last changed: 2026-11-13T03:03:31Z Last verified: 2026-11-20T12:18:45Z Next check: 2026-11-21T12:18:45Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of long-prompt version requirement | v2.1.293 | [1] | 2026-11-20 overrides version requirement | v2.1.227 | [1] | 2026-11-20 mapped model ID version requirement | v2.1.218 | [1] | 2026-11-20 abort floor estimate | about four characters per output token | [1] | 2026-11-20 Sources: [1] Anthropic. "Claude apps gateway spend limits". https://code.claude.com/docs/en/claude-apps-gateway-spend-limits.md Role: primary. Accessed: 2026-11-20T12:18:45Z Quote: "a gateway server running Claude Code v2.1.293 or later prices the whole request at that rate" (Supports: long-prompt version requirement) Quote: "Requires v2.1.227 or later." (Supports: overrides version requirement) Quote: "Requires v2.1.218 or later." (Supports: mapped model ID version requirement) Quote: "the meter bills a floor estimate of about four characters per output token" (Supports: abort floor estimate) Published: 2026-11-20T03:10:57Z Snapshot SHA-256: 0cd60cadc3fda9d8f2882dbeb78616eb5e17597f4a26a75d0e184044a1eeb165 (captured 2026-11-13T03:03:30Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T03:03:31Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:18:45Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:18:45Z Last attempt: 2026-11-20T12:18:45Z Notes and limitations: Extracted automatically from a single official source (section "How requests are priced"). Related: https://latestn.com/tool/claude-code/pricing-and-limits/review-skipped-budget-message Why did Claude Code Review skip my pull request with a budget message? https://latestn.com/tool/claude-code/pricing-and-limits/scheduled-task-limits What are the usage limits for Claude Code scheduled tasks? https://latestn.com/tool/claude-code/pricing-and-limits/spend-limit-enforcement How does the Claude apps gateway enforce spend limits and what happens when a developer hits their cap? https://latestn.com/tool/claude-code/pricing-and-limits/mod-limits What limits apply to Claude Code mods? https://latestn.com/tool/claude-code/pricing-and-limits/per-step-per-model-usage How do I track per-step and per-model token usage in the Claude Agent SDK? https://latestn.com/tool/claude-code/pricing-and-limits/reduce-token-usage How can I reduce token usage in Claude Code? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:03:31Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/pricing-and-limits/request-pricing-long-prompts/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/pricing-and-limits/request-pricing-long-prompts POST: https://latestn.com/dispute/tool/claude-code/pricing-and-limits/request-pricing-long-prompts with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/pricing-and-limits/request-pricing-long-prompts?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How are requests priced against Claude apps gateway spend limits, including long-prompt rates? Revision 1, last verified 2026-11-20T12:18:45Z. https://latestn.com/tool/claude-code/pricing-and-limits/request-pricing-long-prompts (accessed 2026-11-21T10:03:03Z). @misc{LatestN_tool_claude_code_pricing_and_limits_request_pricing_long_prompts_r1, title = {How are requests priced against Claude apps gateway spend limits, including long-prompt rates?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/pricing-and-limits/request-pricing-long-prompts}}, note = {Revision 1; digest sha256:bfcdd7600349e508; last verified 2026-11-20T12:18:45Z; accessed 2026-11-21T10:03:03Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/pricing-and-limits/request-pricing-long-prompts