Claude Haiku 5.5 Is Cheap Until 100k Tokens. Build a Tiny Price Gate in TypeScript.

A developer published a TypeScript price gate for Anthropic's Claude Haiku 5.5, released October 7, 2026, that returns ALLOW, REVIEW, or REFUSE before a request is sent based on prompt size, task type, and effort level. The gate applies Haiku 5.5's short-tier rates ($0.10/$0.50 per million input/output tokens) only up to 100,000 prompt tokens, switching to long-tier rates ($0.50/$2.50) and a REVIEW decision above that line, and flags agentic-coding and computer-use tasks for review even on short prompts, citing Anthropic's Terminal-Bench 4.0 scores of 39.2% for Haiku 5.5 versus 70.6% for Sonnet 5.5. It also accounts for the new tokenizer's roughly 30% higher token count and the model's low/medium/high/xhigh/max effort dial, defaulting to medium when effort is omitted.

On October 7, 2026, Anthropic released Claude Haiku 5.5. The model id is claude-haiku-5-5 . For prompts up to 100,000 tokens, input is $0.10 per million tokens and output is $0.50. That is 90% below Haiku 4.5's $1.00 and $5.00. Cross 100,000 tokens and the rates become $0.50 and $2.50. That is a 50% cut, not a 90% cut. Anthropic also says the new tokenizer uses about 30% more tokens than Haiku 4.5 for the same text. A cheaper token is not automatically a cheaper task. And Haiku 5.5 is the first Haiku with an effort dial. The API default is medium . low , high , xhigh , and max are real settings. They change how much the model thinks, which changes the bill. The list price does not tell you that. The useful question is what your code does before the request leaves. This toy does not call Claude. You hand it token counts you already have, a task name, and an effort. It answers ALLOW, REVIEW, or REFUSE, and it prints the list-price bill in USD. Prompt size is input tokens plus cache reads plus cache writes. At or under 100,000, the short rates apply. Over that line, the long rates apply and the decision is REVIEW. ALLOW is only for five narrow jobs: classify , extract , route , summarize , and compact . Effort must be low or medium . If you omit effort, the gate stamps medium , because that is the Claude API default for this model. agentic-coding and computer-use are REVIEW even on a short prompt. Anthropic's own Terminal-Bench 4.0 numbers are 39.2% for Haiku 5.5 and 70.6% for Sonnet 5.5. A lower price is not the same job. high , xhigh , and max are also REVIEW. This program has no eval that says those levels pay for themselves. Bad counts and unknown labels are REFUSE. A negative token count should not become a discount. The full source is below. Save it as src/gate.ts . Node 22 or newer. No packages. No key. node --experimental-strip-types src/gate.ts / Price gate for Claude Haiku 5.5. No network. No API key. Rates are list prices in microdollars per million tokens. Sources, read 2026-10-08: - https://www.anthropic.com/claude-haiku-5-5 October 7, 2026 - https://platform.claude.com/docs/en/models/haiku-5-5/overview - https://platform.claude.com/docs/en/build-with-claude/effort / const MILLION = 1 000 000n; const PROMPT LIMIT = 100 000n; const RECOUNT NUM = 130n; const RECOUNT DEN = 100n; const ALLOW TASKS = new Set "classify", "extract", "route", "summarize", "compact", ; const REVIEW TASKS = new Set "agentic-coding", "computer-use" ; const ALLOW EFFORT = new Set "low", "medium" ; const ALL EFFORT = new Set "low", "medium", "high", "xhigh", "max" ; type Effort = "low" | "medium" | "high" | "xhigh" | "max"; type Ttl = "5m" | "1h"; type Tier = "short" | "long"; type Rates = { input: bigint; output: bigint; cacheRead: bigint; cacheWrite5m: bigint; cacheWrite1h: bigint; }; const HAIKU 55: Record<Tier, Rates = { short: { input: 100 000n, output: 500 000n, cacheRead: 10 000n, cacheWrite5m: 125 000n, cacheWrite1h: 200 000n, }, long: { input: 500 000n, output: 2 500 000n, cacheRead: 50 000n, cacheWrite5m: 625 000n, cacheWrite1h: 1 000 000n, }, }; const HAIKU 45 5M: Rates = { input: 1 000 000n, output: 5 000 000n, cacheRead: 100 000n, cacheWrite5m: 1 250 000n, cacheWrite1h: 0n, }; const SONNET 55 CACHE READ NEW = 100 000n; const SONNET 55 CACHE READ OLD = 200 000n; export type Job = { name: string; task: string; effort?: string; inputTokens: number; outputTokens: number; cacheReadTokens: number; cacheWriteTokens: number; cacheWriteTtl?: Ttl; recountFromHaiku45?: boolean; }; export type Decision = "ALLOW" | "REVIEW" | "REFUSE"; export type Quote = { name: string; decision: Decision; reason: string; model: "claude-haiku-5-5"; effort: Effort | null; assumedDefaultEffort: boolean; tier: Tier | null; promptTokens: bigint | null; haiku55Usd: string | null; haiku45Usd: string | null; savingsBps: number | null; sonnetCacheReadNewUsd: string | null; sonnetCacheReadOldUsd: string | null; }; function isWhole value: number : boolean { return Number.isFinite value && Number.isInteger value && value = 0; } function mulDiv tokens: bigint, perMillion: bigint : bigint { return tokens perMillion / MILLION; } function usd micro: bigint : string { const whole = micro / MILLION; const frac = micro % MILLION .toString .padStart 6, "0" ; return ${whole}.${frac} ; } function bill tokens: { input: bigint; output: bigint; cacheRead: bigint; cacheWrite: bigint; }, rates: Rates, ttl: Ttl : bigint { const writeRate = ttl === "1h" ? rates.cacheWrite1h : rates.cacheWrite5m; return mulDiv tokens.input, rates.input + mulDiv tokens.output, rates.output + mulDiv tokens.cacheRead, rates.cacheRead + mulDiv tokens.cacheWrite, writeRate ; } function savingsBps before: bigint, after: bigint : number | null { if before <= 0n return null; return Number before - after 10 000n / before ; } export function quoteJob job: Job : Quote { const base = { name: job.name, model: "claude-haiku-5-5" as const, effort: null, assumedDefaultEffort: false, tier: null, promptTokens: null, haiku55Usd: null, haiku45Usd: null, savingsBps: null, sonnetCacheReadNewUsd: null, sonnetCacheReadOldUsd: null, }; const counts = job.inputTokens, job.outputTokens, job.cacheReadTokens, job.cacheWriteTokens, ; if counts.every isWhole { return { ...base, decision: "REFUSE", reason: "token counts must be non-negative integers", }; } const ttl = job.cacheWriteTtl ?? "5m"; if ttl == "5m" && ttl == "1h" { return { ...base, decision: "REFUSE", reason: "cache write ttl must be 5m or 1h" }; } let effort = job.effort; let assumedDefaultEffort = false; if effort === undefined { effort = "medium"; assumedDefaultEffort = true; } if ALL EFFORT.has effort { return { ...base, decision: "REFUSE", reason: unknown effort ${job.effort} }; } const knownTask = ALLOW TASKS.has job.task || REVIEW TASKS.has job.task ; if knownTask { return { ...base, decision: "REFUSE", reason: unknown task ${job.task} }; } let input = BigInt job.inputTokens ; let cacheRead = BigInt job.cacheReadTokens ; let cacheWrite = BigInt job.cacheWriteTokens ; const output = BigInt job.outputTokens ; if job.recountFromHaiku45 { input = input RECOUNT NUM / RECOUNT DEN; cacheRead = cacheRead RECOUNT NUM / RECOUNT DEN; cacheWrite = cacheWrite RECOUNT NUM / RECOUNT DEN; } const promptTokens = input + cacheRead + cacheWrite; const tier: Tier = promptTokens <= PROMPT LIMIT ? "short" : "long"; const haiku55 = bill { input, output, cacheRead, cacheWrite }, HAIKU 55 tier , ttl, ; let haiku45: bigint | null = null; if ttl === "5m" { const oldInput = BigInt job.inputTokens ; const oldRead = BigInt job.cacheReadTokens ; const oldWrite = BigInt job.cacheWriteTokens ; haiku45 = bill { input: oldInput, output, cacheRead: oldRead, cacheWrite: oldWrite }, HAIKU 45 5M, "5m", ; } const reasons: string = ; if ALLOW TASKS.has job.task { reasons.push ${job.task} stays off the Haiku allow-list ; } if ALLOW EFFORT.has effort { reasons.push effort ${effort} needs an eval this toy does not have ; } if tier === "long" { reasons.push "prompt is over 100000 tokens, so the long-tier rates apply" ; } if job.recountFromHaiku45 { reasons.push "prompt tokens were recounted at 130/100 before the Haiku 5.5 bill" ; } if assumedDefaultEffort { reasons.push "missing effort was stamped medium, the API default" ; } const decision: Decision = reasons.some reason = reason.startsWith "prompt is over" || reason.includes "allow-list" || reason.includes "needs an eval" ? "REVIEW" : "ALLOW"; if decision === "ALLOW" { reasons.unshift "short prompt, allow-listed task, effort is low or medium" ; } if ttl === "1h" { reasons.push "one-hour cache writes are quoted for Haiku 5.5 only" ; } const sonnetNew = mulDiv cacheRead, SONNET 55 CACHE READ NEW ; const sonnetOld = mulDiv BigInt job.cacheReadTokens , SONNET 55 CACHE READ OLD ; return { ...base, decision, reason: reasons.join "; " , effort: effort as Effort, assumedDefaultEffort, tier, promptTokens, haiku55Usd: usd haiku55 , haiku45Usd: haiku45 === null ? null : usd haiku45 , savingsBps: haiku45 === null ? null : savingsBps haiku45, haiku55 , sonnetCacheReadNewUsd: usd sonnetNew , sonnetCacheReadOldUsd: usd sonnetOld , }; } function line quote: Quote : string { const parts = quote.name, quote.decision, quote.model, quote.effort === null ? "effort=none" : effort=${quote.effort} , quote.tier === null ? "tier=none" : tier=${quote.tier} , quote.promptTokens === null ? "prompt=none" : prompt=${quote.promptTokens} , quote.haiku55Usd === null ? "haiku55=none" : haiku55=${quote.haiku55Usd} , quote.haiku45Usd === null ? "haiku45=none" : haiku45=${quote.haiku45Usd} , quote.savingsBps === null ? "savings bps=none" : savings bps=${quote.savingsBps} , quote.reason, ; return parts.join " | " ; } const fixtures: Job = { name: "classify-short", task: "classify", effort: "medium", inputTokens: 2 000, outputTokens: 200, cacheReadTokens: 0, cacheWriteTokens: 0, }, { name: "compact-under-limit", task: "compact", effort: "low", inputTokens: 4 000, outputTokens: 500, cacheReadTokens: 80 000, cacheWriteTokens: 0, }, { name: "compact-over-limit", task: "compact", effort: "medium", inputTokens: 20 000, outputTokens: 400, cacheReadTokens: 90 000, cacheWriteTokens: 0, }, { name: "coding-short", task: "agentic-coding", effort: "medium", inputTokens: 8 000, outputTokens: 1 200, cacheReadTokens: 0, cacheWriteTokens: 0, }, { name: "classify-max-effort", task: "classify", effort: "max", inputTokens: 2 000, outputTokens: 200, cacheReadTokens: 0, cacheWriteTokens: 0, }, { name: "extract-default-effort", task: "extract", inputTokens: 1 500, outputTokens: 300, cacheReadTokens: 0, cacheWriteTokens: 0, }, { name: "recount-30", task: "summarize", effort: "medium", inputTokens: 10 000, outputTokens: 500, cacheReadTokens: 0, cacheWriteTokens: 0, recountFromHaiku45: true, }, { name: "one-hour-write", task: "route", effort: "low", inputTokens: 1 000, outputTokens: 100, cacheReadTokens: 0, cacheWriteTokens: 4 000, cacheWriteTtl: "1h", }, { name: "bad-tokens", task: "classify", effort: "low", inputTokens: -1, outputTokens: 10, cacheReadTokens: 0, cacheWriteTokens: 0, }, { name: "unknown-effort", task: "classify", effort: "turbo", inputTokens: 100, outputTokens: 10, cacheReadTokens: 0, cacheWriteTokens: 0, }, ; const expected: Record<string, { decision: Decision; haiku55Usd: string | null; savingsBps: number | null } = { "classify-short": { decision: "ALLOW", haiku55Usd: "0.000300", savingsBps: 9000 }, "compact-under-limit": { decision: "ALLOW", haiku55Usd: "0.001450", savingsBps: 9000 }, "compact-over-limit": { decision: "REVIEW", haiku55Usd: "0.015500", savingsBps: 5000 }, "coding-short": { decision: "REVIEW", haiku55Usd: "0.001400", savingsBps: 9000 }, "classify-max-effort": { decision: "REVIEW", haiku55Usd: "0.000300", savingsBps: 9000 }, "extract-default-effort": { decision: "ALLOW", haiku55Usd: "0.000300", savingsBps: 9000 }, "recount-30": { decision: "ALLOW", haiku55Usd: "0.001550", savingsBps: 8760 }, "one-hour-write": { decision: "ALLOW", haiku55Usd: "0.000950", savingsBps: null }, "bad-tokens": { decision: "REFUSE", haiku55Usd: null, savingsBps: null }, "unknown-effort": { decision: "REFUSE", haiku55Usd: null, savingsBps: null }, }; function main : void { let failed = 0; for const job of fixtures { const quote = quoteJob job ; const want = expected job.name ; const ok = want.decision === quote.decision && want.haiku55Usd === quote.haiku55Usd && want.savingsBps === quote.savingsBps; if ok { failed += 1; console.error FAIL ${job.name} ; console.error quote ; } console.log line quote ; } const cacheRead = 100 000n; const sonnetNew = usd mulDiv cacheRead, SONNET 55 CACHE READ NEW ; const sonnetOld = usd mulDiv cacheRead, SONNET 55 CACHE READ OLD ; console.log sonnet-cache-read | QUOTE | claude-sonnet-5-5 | cache read tokens=100000 | new=${sonnetNew} | old=${sonnetOld} | October 7 cache-read cut, not a routing decision , ; if sonnetNew == "0.010000" || sonnetOld == "0.020000" { failed += 1; console.error "FAIL sonnet-cache-read" ; } if failed 0 { console.error ${failed} check s failed ; process.exit 1 ; } console.log checks=11 passed ; } main ; Checked on October 8, 2026, Node.js 25.6.0. Eleven checks passed: classify-short | ALLOW | claude-haiku-5-5 | effort=medium | tier=short | prompt=2000 | haiku55=0.000300 | haiku45=0.003000 | savings bps=9000 | short prompt, allow-listed task, effort is low or medium compact-under-limit | ALLOW | claude-haiku-5-5 | effort=low | tier=short | prompt=84000 | haiku55=0.001450 | haiku45=0.014500 | savings bps=9000 | short prompt, allow-listed task, effort is low or medium compact-over-limit | REVIEW | claude-haiku-5-5 | effort=medium | tier=long | prompt=110000 | haiku55=0.015500 | haiku45=0.031000 | savings bps=5000 | prompt is over 100000 tokens, so the long-tier rates apply coding-short | REVIEW | claude-haiku-5-5 | effort=medium | tier=short | prompt=8000 | haiku55=0.001400 | haiku45=0.014000 | savings bps=9000 | agentic-coding stays off the Haiku allow-list classify-max-effort | REVIEW | claude-haiku-5-5 | effort=max | tier=short | prompt=2000 | haiku55=0.000300 | haiku45=0.003000 | savings bps=9000 | effort max needs an eval this toy does not have extract-default-effort | ALLOW | claude-haiku-5-5 | effort=medium | tier=short | prompt=1500 | haiku55=0.000300 | haiku45=0.003000 | savings bps=9000 | short prompt, allow-listed task, effort is low or medium; missing effort was stamped medium, the API default recount-30 | ALLOW | claude-haiku-5-5 | effort=medium | tier=short | prompt=13000 | haiku55=0.001550 | haiku45=0.012500 | savings bps=8760 | short prompt, allow-listed task, effort is low or medium; prompt tokens were recounted at 130/100 before the Haiku 5.5 bill one-hour-write | ALLOW | claude-haiku-5-5 | effort=low | tier=short | prompt=5000 | haiku55=0.000950 | haiku45=none | savings bps=none | short prompt, allow-listed task, effort is low or medium; one-hour cache writes are quoted for Haiku 5.5 only bad-tokens | REFUSE | claude-haiku-5-5 | effort=none | tier=none | prompt=none | haiku55=none | haiku45=none | savings bps=none | token counts must be non-negative integers unknown-effort | REFUSE | claude-haiku-5-5 | effort=none | tier=none | prompt=none | haiku55=none | haiku45=none | savings bps=none | unknown effort turbo sonnet-cache-read | QUOTE | claude-sonnet-5-5 | cache read tokens=100000 | new=0.010000 | old=0.020000 | October 7 cache-read cut, not a routing decision checks=11 passed savings bps is basis points against a Haiku 4.5 bill at the original token counts. 9000 is 90.00%. 5000 is 50.00%. 8760 is 87.60%. Read three of those lines closely. classify-short is the brochure case. 2,000 input tokens and 200 output tokens, effort medium . Haiku 5.5 is $0.000300. Haiku 4.5 is $0.003000. Same tokens, 90% less. compact-over-limit is the line you can miss. 20,000 fresh input tokens plus 90,000 cache-read tokens is a 110,000-token prompt. The job is still compact , which is on the allow-list, and effort is still medium . The decision is REVIEW. Haiku 5.5 costs $0.015500. Haiku 4.5 costs $0.031000. The saving is 50%, because the long-tier rates are five times the short-tier rates, and Haiku 4.5's flat rate is ten times the short-tier rate. recount-30 starts from a Haiku 4.5 count of 10,000 input tokens and 500 output tokens. The gate multiplies the input by 130/100 before it prices Haiku 5.5, so the new bill uses 13,000 input tokens. Haiku 5.5 is $0.001550. Haiku 4.5 is $0.012500. That is 87.60% less, not 90%. The last quote is not a route. On October 7, Anthropic cut Sonnet 5.5 cache reads from $0.20 to $0.10 per million tokens. 100,000 cache-read tokens are $0.010000 now and were $0.020000. The gate prints that. It does not send the job to Sonnet. max on a classify job still shows the short-tier list price, then REVIEW. haiku45 empty. Rates used, USD per million tokens: | Rate | Haiku 5.5, prompt ≤100k | Haiku 5.5, prompt 100k | Haiku 4.5 | |---|---|---|---| | Input | 0.10 | 0.50 | 1.00 | | Output | 0.50 | 2.50 | 5.00 | | Cache read | 0.01 | 0.05 | 0.10 | | Cache write, 5 min | 0.125 | 0.625 | 1.25 | | Cache write, 1 hour | 0.20 | 1.00 | not compared | I'm building Roster, AI employees that do real work. A smaller model still needs a gate that knows which price it is about to pay.