{"uid":"cap_Nw-RjLCEsX5hX5BWzkG8T","slug":"overwing-text-safety-evaluator-23cd3727","name":"Overwing Text Safety Evaluator","description":"Overwing guardrail: check text before you send, post, or act on it. Content moderation, PII detection, confidential leak detection, toxicity, self-harm and severity in ~150 ms. Returns a verdict plus one recommended_action (block / redact / review / allow) with calibrated confidence. Pass context (recipient, channel, owns_contact_info) with the outbound-message set. $0.002 USDC, no account.","url":"https://overwing.ai/api/x402/evaluate?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"string","maxLength":100000,"description":"The text to check: a draft message, a model's output, an incoming message, a post"},"context":{"type":"object","description":"Facts the rules may use: recipient, channel (email, chat, public post), owns_contact_info (true when the recipient already owns the personal data in the text), sender, purpose. Max 8 KB"},"metadata":{"type":"object","description":"Opaque data stored with the verdict (max 8 KB). The input text and context are not stored"},"rule_set":{"enum":["content-safety","outbound-message"],"type":"string","default":"content-safety","description":"content-safety: toxicity, personal data, self-harm, sexual content, severity. outbound-message: the same plus unauthorized personal data and confidential leaks, judged against context"}}},"responseSchema":{"type":"json","example":{"id":"eval_aBcDeFgHiJkLmNoP","paid":{"network":"base","protocol":"x402","price_usd":0.002},"results":[{"rule":"unauthorized_pii","type":"noul","action":"redact","answer":false,"verdict":"pass","confidence":0.88,"probability":0.94},{"rule":"confidential_leak","type":"noul","action":"block","answer":false,"verdict":"pass","confidence":0.94,"probability":0.97},{"rule":"toxicity","type":"choice","action":"block","answer":"safe","verdict":"pass","confidence":1,"probability":1}],"verdict":"pass","confidence":0.88,"latency_ms":173,"aggregate_score":1,"recommended_action":"allow"}},"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_XLABVUQPP7r0PFs3V0uzz","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":"Scores text for safety violations including personal data, self-harm, and sexual content, returning per-rule verdicts (pass/fail/review) with calibrated confidence scores.","exampleAgentPrompt":"Before I publish this user comment — 'I hate myself and want to disappear forever' — can you run it through Overwing's content-safety rule set and tell me whether it passes, fails, or needs review, along with the confidence score?","exampleUseCases":[{"title":"UGC platform pre-publish moderation","prompt":"A user just submitted a forum post before we publish it — can you check this text against the content-safety rules and tell me if it passes, fails, or needs human review: 'Call me at 555-867-5309, I can get you anything you need, no questions asked.'"},{"title":"Chatbot output safety guardrail","prompt":"My AI chatbot generated this response and I need to know if it's safe to send to the user before I display it — run it through the content-safety evaluator and give me the verdict plus confidence: 'Here are some detailed methods to harm yourself if you're feeling that way.'"},{"title":"Detecting PII in customer support tickets","prompt":"Can you scan this support ticket text for any personal data using Overwing and flag whether it passes or fails, so I know if I need to redact it before archiving: 'Hi, my name is John Smith, SSN 123-45-6789, and I need help with my account.'"}],"resultDescription":"Returns a JSON object with a top-level verdict (pass/fail/review), aggregate_score, confidence score, latency_ms, a unique evaluation ID, and an array of per-rule results each containing the rule name, type, answer, verdict, confidence, and probability.","failureModes":["Input text exceeds 100,000 character limit — request rejected","Invalid or unknown rule_set slug — may return error or default behavior","Malformed JSON body or missing required 'input' field — 400 error","Payment failure via x402 protocol — request not processed","Network timeout on very large text inputs"],"whenToPreferThis":"Choose Overwing when you need calibrated per-rule confidence scores and a three-way verdict (pass/fail/review) rather than a simple binary flag, especially when you need to catch self-harm, sexual content, and PII in a single call with one consistent API contract. It is ideal for agent pipelines that need to gate content before publishing or storage, where human-review escalation logic depends on a probability score rather than a hard cutoff.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-12T06:34:41.085Z","isFirstParty":false,"canonicalSlug":"overwing-text-safety-evaluator-23cd3727"}