{"uid":"cap_tI3oSwIavDEnoTqnk2muF","slug":"oblique-markets-text-classifier-139eba4e","name":"Oblique Markets Text Classifier","description":"Use when an agent needs classify. Returns Single-label text classification against 2-20 caller-supplied labels — reply validated against the label set, canonical label returned, 502 instead of hallucinated labels. $0.005.","url":"https://api.oblique.markets/api/v1/paid/classify","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"text":{"type":"string","description":"Text to classify; truncated to 8,000 characters"},"labels":{"type":"array","items":{"type":"string"},"description":"Candidate labels; exactly one is returned"}}},"responseSchema":{"type":"json","example":{"label":"billing_issue","model":"inclusionai/ling-3.0-flash"}},"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_PFm7O3vUDSiEJgfhe_H4a","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":"Classifies a piece of text into one of 2–20 caller-supplied labels using an LLM, returning only a validated canonical label (never a hallucinated one) or a 502 error.","exampleAgentPrompt":"Classify this support ticket — 'My order never arrived and I want a refund' — into one of these labels: billing, shipping, returns, technical, general. Make sure you only return one of those exact labels.","exampleUseCases":[{"title":"Support ticket routing by category","prompt":"I have an incoming support message: 'The app keeps crashing when I try to log in.' Can you classify it into one of these categories: account, billing, bug, feature-request, general? I only want back one of those exact labels."},{"title":"Content moderation label assignment","prompt":"Classify this user-submitted comment — 'Go buy followers, this is trash' — into one of these labels: spam, harassment, misinformation, safe. Only return one of those exact labels, nothing else."},{"title":"Expense transaction categorization","prompt":"I have a bank transaction description: 'UBER EATS ORDER 8843'. Classify it into one of these expense categories: food, transport, accommodation, entertainment, utilities. Give me just the matching label."}],"resultDescription":"A single canonical label drawn exactly from the caller-supplied label set. The response is validated against that set — if the LLM would otherwise produce something outside the list, the endpoint returns a 502 rather than a hallucinated label. Agents receive a clean, machine-readable string with no extra explanation.","failureModes":["502 returned when the LLM cannot confidently map the text to any of the supplied labels — prevents hallucinated or out-of-set labels","Input text is ambiguous or too short for any label to be meaningful — 502 or unexpected label","Fewer than 2 or more than 20 labels supplied — likely a 4xx validation error","Payment failure via x402 — endpoint refuses request before classification is attempted","Latency spike if underlying LLM is under load — retries may be needed"],"whenToPreferThis":"Choose this endpoint when you need guaranteed label fidelity — i.e., you cannot tolerate an LLM returning a label outside your predefined set. It is ideal for deterministic routing pipelines, compliance-sensitive categorization, or any workflow where a hallucinated label would cause a downstream error. Prefer it over a raw LLM call when you need a strict enum-like output with no free-text drift. It pays per call at $0.005 USDC, making it cost-effective for high-volume classification tasks that don't need a full generative response.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:41:55.323Z","isFirstParty":false}