{"uid":"cap_UMTC1moa2o0lzUBYWUOxI","slug":"sift-web-tools-text-classifier-68a98212","name":"Sift Web Tools Text Classifier","description":"Sentiment, emotions, topics and toxicity of text, optionally sorted into your own labels. Analyses up to 4000 characters: language, sentiment and score (-1 to 1), up to 3 emotions, topics, toxicity and a one-line summary. Pass labels=a,b,c to sort the text into your own categories with a score for each.","url":"https://sift.srv1996466.hstgr.cloud/v1/classify?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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["text"],"properties":{"text":{"type":"string","description":"Text to analyse (max 4000 chars)"},"labels":{"type":"string","description":"Optional comma-separated labels"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"label":"complaint","language":"English","toxicity":"none","sentiment":"negative","sentiment_score":-0.7}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JYN1hHOzqrrmSA34w_59t","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Analyzes text (up to 4000 chars) for language, sentiment, emotions, topics, toxicity, and optionally sorts it into user-defined labels","exampleAgentPrompt":"Can you analyze this customer review for sentiment, emotions, and toxicity, and also classify it as either 'complaint', 'praise', or 'suggestion'? Here's the text: 'The delivery was shockingly late and no one bothered to notify me — absolutely unacceptable service.'","exampleUseCases":[{"title":"Moderation pipeline for user comments","prompt":"Check this forum post for toxicity and flag any harmful emotions before it goes live: 'People like you should just disappear, nobody wants your opinion here.'"},{"title":"Support ticket routing by custom label","prompt":"Classify this support message into one of these categories — 'billing', 'technical', or 'general' — and give me a sentiment score so I know how urgent it is: 'I was charged twice this month and nobody has responded to my emails for a week.'"},{"title":"Social media brand sentiment monitoring","prompt":"Analyze this tweet about our brand for sentiment, the top emotions it conveys, and give me a one-line summary: 'Honestly blown away by how fast the team resolved my issue — best customer support I've ever experienced!'"}],"resultDescription":"A JSON object containing: detected language, overall sentiment label (positive/negative/neutral), a numeric sentiment score from -1 to 1, up to 3 emotions present in the text, relevant topics, a toxicity level (e.g. none/mild/high), a one-line summary, and if labels were provided, a score for each custom label indicating how well the text fits that category.","failureModes":["Text exceeds 4000 characters — the endpoint may truncate or reject the input","Missing required 'text' query parameter — returns an error","Ambiguous or very short text may yield low-confidence or generic sentiment scores","Malformed labels parameter (not comma-separated) may be ignored or cause unexpected results","Non-English text may have reduced accuracy for emotion and topic detection"],"whenToPreferThis":"Choose this endpoint when you need a combined multi-signal text analysis in a single call — sentiment score, emotions, topics, toxicity, language detection, and a summary — especially when you also want to sort text into your own custom label taxonomy. It is well-suited for content moderation, customer feedback triage, and brand monitoring pipelines where multiple NLP signals are needed simultaneously without chaining multiple API calls.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-20T12:36:12.098Z","isFirstParty":false,"canonicalSlug":"sift-web-tools-text-classifier-68a98212"}