{"uid":"cap_puXoVfvvOU6sa1x7tUcTE","slug":"macaroon-network-gpu-llm-pricing-change-detector-6f9a43de","name":"Macaroon Network GPU LLM Pricing Change Detector","description":"Per-target pricing change events -- whether the latest scraped snapshot differs from the previous one, with fetch times and content hashes for both. No outbound network on purchase; read from the local feed database populated by the scraper on a 6-hour cadence.","url":"https://api.macaroonnetwork.com/execute/polymathica-gpu-llm-pricing-changes-v1","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object"},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_dzySC5FEa3ZpnNCE7Dyog","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Returns per-target pricing change events for GPU/LLM services, indicating whether the latest scraped snapshot differs from the previous one, including fetch timestamps and content hashes for both snapshots.","exampleAgentPrompt":"Check whether the pricing for any GPU or LLM providers has changed since the last scrape — I want to know if the current snapshot differs from the previous one, along with the fetch times and content hashes for both.","exampleUseCases":[{"title":"LLM price change alert pipeline","prompt":"Has any LLM provider pricing page changed in the last scrape cycle? I need the change flag, the fetch timestamps, and both content hashes so I can trigger a downstream alert if something differs."},{"title":"GPU cloud cost tracking for ML budget","prompt":"Pull the latest pricing change events for GPU cloud services — I want to know which targets showed a difference between the current and previous snapshot so I can update our ML infrastructure cost model."},{"title":"Competitive AI pricing intelligence","prompt":"I'm tracking competitor LLM API prices — can you check whether any of the monitored pricing pages have a new snapshot that differs from the previous one, and give me the content hashes and fetch times for both?"}],"resultDescription":"A pricing change event object per target indicating whether the current scraped snapshot differs from the previous one, along with fetch timestamps for both snapshots and their respective content hashes, read from a local feed database updated on a 6-hour cadence. No live network fetch is performed on purchase.","failureModes":["Target not found in local feed database — no event returned","Feed not yet populated for a new target — missing previous snapshot","Stale data if scraper cadence is delayed beyond 6 hours","Invalid or malformed target identifier — request error","Schema mismatch if body is not valid JSON POST payload"],"whenToPreferThis":"Choose this endpoint when you need lightweight, low-latency detection of GPU or LLM pricing page changes without triggering live web fetches. It reads from a pre-populated local database updated on a 6-hour cadence, making it ideal for polling or event-driven pipelines that need content-hash-based diffing rather than full page retrieval. Prefer it over live scrapers when cost, rate-limit avoidance, or reproducibility matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:50:08.470Z","isFirstParty":false}