{"uid":"cap_eKvyr_8rd7fldLGnwBR61","slug":"llm-cost-capacity-calc-batch-discount-savings-0daf5a01","name":"LLM Cost & Capacity Calc – Batch Discount Savings","description":"Compare realtime and batch API cost for a workload with your discount fraction, and the money saved by waiting.","url":"https://llm-cost-calc.x402tookit.com/batch-discount?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["inputTokens","outputTokens","requests","inputPricePerMTok","outputPricePerMTok"],"properties":{"requests":{"type":"integer","description":"Number of requests, 1 to 1e9"},"inputTokens":{"type":"number","description":"Input tokens per request"},"outputTokens":{"type":"number","description":"Output tokens per request"},"batchDiscount":{"type":"number","description":"Batch discount as a fraction, 0 to 1 (default 0.5 = 50% off)"},"inputPricePerMTok":{"type":"number","description":"Realtime price per million input tokens"},"outputPricePerMTok":{"type":"number","description":"Realtime price per million output tokens"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"asOf":{"type":["null","string"]},"source":{"type":["null","string"]},"reasons":{"type":["array","null"],"items":{"type":"string"}},"savings":{"type":["null","number"]},"summary":{"type":["null","string"]},"verdict":{"type":["null","string"]},"degraded":{"type":["boolean","null"]},"requests":{"type":["null","number"]},"batchCost":{"type":["null","number"]},"disclaimer":{"type":["null","string"]},"notChecked":{"type":["array","null"],"items":{"type":"string"}},"realtimeCost":{"type":["null","number"]},"discountPercent":{"type":["null","number"]},"batchCostPerRequest":{"type":["null","number"]},"realtimeCostPerRequest":{"type":["null","number"]}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ENQb09e5DIkWEkkEgFHZ3","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Compares realtime vs. batch API cost for an LLM workload given token counts, prices, and a discount fraction, and returns how much money is saved by using batch mode.","exampleAgentPrompt":"How much would I save using batch mode instead of realtime for a job of 50,000 requests, each with 800 input tokens and 200 output tokens, at $5 per million input tokens and $15 per million output tokens, with a 50% batch discount?","exampleUseCases":[{"title":"Evaluate batch savings for annotation pipeline","prompt":"I'm running a data annotation job — 200,000 requests, 500 input tokens and 100 output tokens each, at $3 per million input and $10 per million output. With a 50% batch discount, how much would I save by using batch mode instead of realtime?"},{"title":"Decide whether batch delay is worth it for nightly summaries","prompt":"We run 5,000 document summaries overnight with 2,000 input tokens and 400 output tokens each. Our provider charges $8 per million input and $20 per million output tokens. With a 50% batch discount, what's the cost difference between realtime and batch, and is waiting worth it?"},{"title":"Compare batch vs realtime cost for model fine-tune eval runs","prompt":"I need to evaluate outputs for 1,000,000 requests with 300 input tokens and 50 output tokens at $1.50 per million input and $2 per million output tokens. Apply the default 50% batch discount and tell me the total savings and cost per request for both modes."}],"resultDescription":"Returns realtime total cost, batch total cost, savings amount, discount percent applied, cost per request for both modes, a verdict on whether batch is worth it, a human-readable summary, and optional reasons or disclaimers. May also include degraded/source/asOf metadata fields.","failureModes":["Missing required query parameters (inputTokens, outputTokens, requests, inputPricePerMTok, outputPricePerMTok) returns an error","Non-numeric or out-of-range values (e.g. requests > 1e9 or batchDiscount > 1) may return validation errors","Service degradation indicated by degraded=true flag in response with partial results","Payment failure via x402 protocol blocks access if USDC balance is insufficient"],"whenToPreferThis":"Use this endpoint when you need a quick, structured comparison of batch vs. realtime LLM API costs for a defined workload — especially when you have your own per-million-token prices and want to quantify savings from a specific discount fraction. Prefer it over manual spreadsheet math or generic cost calculators when building automated pipelines that need to decide whether to queue work for batch or process immediately.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-29T13:13:41.265Z","isFirstParty":false,"canonicalSlug":"llm-cost-capacity-calc-batch-discount-savings-0daf5a01"}