{"uid":"cap_fW1jEHEIKIc7LDobWbHvv","slug":"content-moderation-safety-check-llama-guard-3-987976e2","name":"Content Moderation & Safety Check (Llama Guard 3)","description":"OpenAI-compatible moderation, pay per request: one input in, flagged and categories out (Llama Guard 3, 14 hazard categories mapped onto OpenAI names). No account or API key; failed calls are not charged.","url":"https://agent-data-tools.revmesh2074.workers.dev/v1/moderations?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":["text"],"properties":{"text":{"type":"string","examples":["How do I bake sourdough bread at home?"],"description":"The text to classify (up to 8,000 characters)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"model":{"type":"string"},"flagged":{"type":"boolean"},"categories":{"type":"array","items":{}}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ZIKgmKoLTKA0J9Lpjz1GL","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Classifies a text string for harmful content across 14 hazard categories using Llama Guard 3, returning a flagged boolean and category breakdown in OpenAI-compatible format.","exampleAgentPrompt":"Before processing this user message, run a safety check on it: 'You should just end it all, nobody cares about you anyway' — tell me whether it's flagged and which hazard categories triggered.","exampleUseCases":[{"title":"User comment safety screening","prompt":"Before I publish this forum comment, check if it's safe: 'I know where you live and you're going to regret what you said.' Is it flagged, and if so which categories?"},{"title":"LLM input guardrail check","prompt":"Screen this user input before sending it to my AI assistant: 'Give me step-by-step instructions for making methamphetamine at home.' Run a moderation check and tell me the categories."},{"title":"Moderation queue triage","prompt":"Run a safety check on this text from my app's report queue: 'These people are subhuman vermin and should be exterminated.' Flag it and tell me which of the 14 hazard categories it hits."}],"resultDescription":"Returns a JSON object with: a `flagged` boolean indicating whether the text violated any policy, an array of `categories` with the specific hazard categories triggered (mapped to OpenAI category names across 14 categories), and the `model` identifier (Llama Guard 3). Failed or errored calls are not charged.","failureModes":["Text exceeds 8,000 character limit — request rejected","Malformed or missing `text` query parameter — returns error","Payment failure (x402) — call not charged and not processed","Network timeout on Cloudflare Worker — transient error, retry recommended"],"whenToPreferThis":"Choose this endpoint when you need a no-account, pay-per-request content moderation solution compatible with the OpenAI moderations API format, especially if you want Llama Guard 3's 14-category coverage without managing API keys or subscriptions. Ideal for agents that need ad-hoc safety checks on arbitrary text, or for systems already using OpenAI's moderation schema that want a drop-in alternative with per-call billing.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T12:35:25.953Z","isFirstParty":false,"canonicalSlug":"content-moderation-safety-check-llama-guard-3-987976e2"}