{"uid":"cap_-fZ1aYhtisOBC3_qKTgWA","slug":"relaystation-llm-text-classifier-725cca9f","name":"Relaystation LLM Text Classifier","description":"Provider cost + 6%, itemized. Assign one label from your label set — routing, triage, moderation. ≈Opus-4.8 accuracy at ~1–5% of its cost (relaystation.ai/llm-validation). 1¢ x402 min; remainder auto-credits — relaystation.ai/penny","url":"https://api.relaystation.ai/v1/llm/classify","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","properties":{"tier":{"enum":["budget","value","best"],"type":"string"},"input":{"type":"string","minLength":1,"description":"The text to process (DATA — never interpolated into the instruction)."},"params":{"type":"object","required":["labels"],"properties":{"labels":{"type":"array","items":{"type":"string"},"minItems":1}},"description":"Task-specific params for 'classify', validated against the task's param_schema."}}},"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","required":["result","truncated","usage"],"properties":{"usage":{"type":"object","required":["model","inputTokens","outputTokens","providerCostMicros","markupPct","chargedMicros","ceilingMicros"],"properties":{"model":{"type":"string"},"markupPct":{"type":"number"},"inputTokens":{"type":"integer"},"outputTokens":{"type":"integer"},"ceilingMicros":{"type":"integer","description":"The authorized ceiling the 402/hold reserved."},"chargedMicros":{"type":"integer","description":"The actual charged amount (<= ceiling)."},"providerCostMicros":{"type":"integer"}}},"result":{"type":"string","description":"The task output text (or JSON string for extract/json_repair)."},"truncated":{"type":"boolean","description":"True when the output hit the per-task token cap; the charge still stands."}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","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__Mk8UZwivWv5fMejxfC7q","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Classifies text into one of a user-defined label set (routing, triage, moderation) using LLM-grade accuracy at a fraction of frontier model cost","exampleAgentPrompt":"Classify this incoming support message — 'My order arrived broken and I need a refund immediately' — using the labels: routing, triage, and escalation. I want near-Opus accuracy but without paying full Opus prices.","exampleUseCases":[{"title":"Customer support ticket routing","prompt":"Classify this support message into one of these categories — billing, technical, or general — so we can route it to the right team: 'I was charged twice for my subscription this month and need a refund.'"},{"title":"Content moderation pipeline","prompt":"I need to label this user-submitted forum post as safe, review-needed, or remove using my moderation label set — can you classify it cheaply at scale? The post is: 'Check out this amazing deal, click here now!!!'"},{"title":"Urgent triage for incoming requests","prompt":"Triage this incoming message as high, medium, or low priority so my team knows what to handle first: 'The production server is down and we're losing customers right now.'"}],"resultDescription":"Returns a single label selected from the provided label set, indicating the classification of the input text. May include a confidence score. Designed to match ~Claude Opus 4.8 accuracy at roughly 1-5% of the cost.","failureModes":["Label not in provided label set — model may return an unexpected value if labels are ambiguous","Empty or very short input text may produce low-confidence or incorrect classification","Label set too large or ambiguous may degrade accuracy","Rate limiting or payment failure if x402 micropayment is not properly initialized","Network timeout for unusually long text inputs"],"whenToPreferThis":"Choose this endpoint when you need high-volume text classification at low cost with near-frontier accuracy. It is ideal when you have a predefined label set (routing, triage, moderation, or custom categories) and cannot afford per-call pricing of full frontier models like Claude Opus. Best suited for pipelines classifying hundreds or thousands of messages per day where cost efficiency is critical but accuracy cannot be sacrificed.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:51:28.379Z","isFirstParty":false}