{"uid":"cap__i0N6UzhqwUgHfPCyuk4O","slug":"omniapi-ai-embeddings-e03205e5","name":"OmniAPI AI Embeddings","description":"444 endpoints across 9+ chains. Crypto, AI, Social, Finance, Weather, Tools. Pay per call in USDC via x402 with 4 facilitators: Dexter, Meridian, FluxA, GoPlausible.","url":"https://omni-api-cyan.vercel.app/api/ai/embeddings","method":"POST","headers":{},"bodySchema":{"type":"object","required":["query"],"properties":{"input":{"type":"string","description":"Input data for the endpoint"},"query":{"type":"string","description":"Search query or input text"},"params":{"type":"object","description":"Additional parameters"}}},"responseSchema":{"type":"object","description":"API response data"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.021615","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":"$0.021615/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.021615","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.021615","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_xgrgus6UeuptLW9kUNZea","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.021615","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 a given text input or query via a pay-per-call USDC endpoint","exampleAgentPrompt":"Can you generate vector embeddings for the text 'The quick brown fox jumps over the lazy dog' so I can use them for semantic similarity search in my RAG pipeline?","exampleUseCases":[{"title":"Semantic search index builder","prompt":"Generate embeddings for this product description — 'Ergonomic mesh office chair with lumbar support and adjustable armrests' — so I can store it in my vector database for semantic search."},{"title":"RAG pipeline document encoding","prompt":"I need to embed this paragraph from my knowledge base so my retrieval-augmented generation system can find it later: 'Company returns policy allows refunds within 30 days of purchase with original receipt.'"},{"title":"Text similarity comparison","prompt":"Can you get me the vector embeddings for the query 'best Italian restaurants near me' so I can compare it against my stored restaurant descriptions and find the closest matches?"}],"resultDescription":"Returns a numerical vector (embedding array) representing the semantic meaning of the input text, suitable for use in similarity search, clustering, classification, or retrieval-augmented generation pipelines.","failureModes":["Missing required 'query' field returns a 400 validation error","Payment failure or insufficient USDC balance blocks the request with a 402 response","Very long input text may exceed token limits and return an error","Malformed JSON body results in a parsing error","Network timeout on the Vercel deployment may cause intermittent 503 errors"],"whenToPreferThis":"Choose this endpoint when you need text embeddings and want to pay per call in USDC via the x402 protocol without managing API keys for a dedicated embedding provider. Useful for lightweight or infrequent embedding needs in crypto-native or agent-to-agent workflows where micropayments are the preferred auth mechanism.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:44:56.497Z","isFirstParty":false}