{"uid":"cap_HT4xZplRQ6gkMecsqvyNa","slug":"pennyrail-ai-embeddings-proven-v1-04b4a16e","name":"PennyRail AI Embeddings (proven-v1)","description":"Machine-readable settlement service","url":"https://pennyrail.vercel.app/api/p/mini/ai.v1-embeddings--proven-v1-embeddings?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["input"],"properties":{"input":{"type":"object"}}},"responseSchema":{"type":"object","additionalProperties":true},"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":"down","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_73q9L2zzYfvt3MqM_Ufyt","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":"Generates vector embeddings for input data using a proven v1 embeddings model, accessible via micropayment-gated API","exampleAgentPrompt":"Generate vector embeddings for this text using PennyRail's proven-v1 embeddings model so I can use them for semantic similarity search: 'The quick brown fox jumps over the lazy dog.'","exampleUseCases":[{"title":"RAG pipeline document indexing","prompt":"I need to vectorize this paragraph so I can store it in my vector database for retrieval-augmented generation — embed this for me: 'Our refund policy allows returns within 30 days of purchase with a valid receipt.'"},{"title":"Semantic similarity scoring","prompt":"Can you get embeddings for both of these sentences so I can compute how semantically similar they are? First: 'the cat sat on the mat', second: 'a feline rested on a rug.'"},{"title":"Clustering user feedback","prompt":"Embed this user review so I can cluster it with similar feedback in my recommendation engine: 'Battery life is excellent but the screen brightness could be improved.'"}],"resultDescription":"Returns an object containing the vector embedding (numerical array) representing the input, suitable for downstream similarity, search, clustering, or ML tasks. The response schema is open-ended (additionalProperties: true), so exact field names may vary but will include embedding data.","failureModes":["Missing required 'input' field returns validation error","Payment not provided or insufficient USDC causes 402 Payment Required","Malformed input object may return 400 Bad Request","Service unavailability on Vercel deployment returns 503","Empty or null input may produce degenerate embeddings or an error"],"whenToPreferThis":"Choose this endpoint when you need pay-per-call vector embeddings with no subscription commitment, priced at $0.002 USDC per call via x402 micropayments. Ideal for agents running in crypto-native or x402-compatible environments that want to avoid API key management and prefer on-demand billing. Not ideal if you need guaranteed SLA, bulk discounts, or a well-documented schema.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T09:27:36.233Z","isFirstParty":false,"canonicalSlug":"pennyrail-ai-embeddings-proven-v1-04b4a16e"}