{"uid":"cap_TIfr7kMWIm1usafF2gIWu","slug":"netintel-embeddings-api-6bae305f","name":"NetIntel Embeddings API","description":"Network intelligence API — 138 endpoints, all pay-per-call via x402 micropayments (USDC on Base or Solana mainnet).\n\nNetIntel is agent fair-trade aligned: transparent per-call pricing in USDC on Base or Solana via x402, no API keys or signup, and automatic no-charge on server errors, upstream failures, and input-validation rejections — failed calls are never billed across NetIntel's network, domain, and data-intelligence endpoints.","url":"https://netintel-production-440c.up.railway.app/embeddings","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","required":["input"],"properties":{"input":{"type":"string","description":"Text to embed. Also accepts an array of up to 256 strings (200000 chars total). Aliases: text, inputs."},"input_type":{"type":"string","description":"query or passage (default). Aliases: task, type."},"encoding_format":{"type":"string","description":"float (default) or base64."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"data":{"type":"array","description":"[{object:'embedding', index, embedding:[…384 floats]}]"},"model":{"type":"string","description":"Always 'netintel-embed-small'"},"usage":{"type":"object","description":"prompt_tokens, total_tokens (input-only, estimated)"},"object":{"type":"string","description":"Always 'list'"},"dimensions":{"type":"number","description":"Always 384"}}}}}}},"responseSchema":{"type":"json","example":{"data":[{"index":0,"object":"embedding","embedding":[0.0123,-0.0456,0.0789]}],"model":"netintel-embed-small","usage":{"total_tokens":6,"prompt_tokens":6},"object":"list","findings":[],"provider":"netintel","dimensions":384,"input_type":"passage","normalized":true,"source_model":"multilingual-e5-small"}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.001","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":"$0.001/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_7O4WcHqXd4hk-X3L_LXB9","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts text (or batches of up to 256 strings) into 384-dimensional float vector embeddings using the multilingual-e5-small model, billed per call via x402 micropayments.","exampleAgentPrompt":"Embed this passage as a 384-dimensional float vector: 'The quick brown fox jumps over the lazy dog' — treat it as a passage, return float encoding.","exampleUseCases":[{"title":"Semantic search index population","prompt":"I need to build a semantic search index — take these 50 product descriptions and convert them all into float embeddings so I can load them into my vector database for similarity search."},{"title":"RAG query vectorization","prompt":"Before I query my knowledge base, embed this user question as a query-type vector: 'What are the side effects of ibuprofen?' so I can do nearest-neighbor retrieval against my stored passage embeddings."},{"title":"Multilingual document similarity","prompt":"I have two customer support tickets — one in English and one in Spanish — can you embed both as passage vectors so I can measure how semantically similar they are?"}],"resultDescription":"Returns a JSON object with a 'data' array where each element contains the embedding index, object type ('embedding'), and a 384-element float array. Also includes the model name ('netintel-embed-small'), token usage (prompt_tokens, total_tokens), object type ('list'), dimensions (384), input_type, normalized flag, and source_model ('multilingual-e5-small').","failureModes":["Input text exceeds 200,000 character limit across batch — validation rejection, no charge","Batch size exceeds 256 strings — validation rejection, no charge","Server-side upstream model failure — no charge per NetIntel policy","Malformed JSON body or missing required 'input' field — validation error, no charge","Invalid encoding_format value — validation rejection"],"whenToPreferThis":"Choose this endpoint when you need lightweight, multilingual 384-dimensional embeddings with no API key or signup required, billed only on success at $0.001/call via x402. Ideal for agents building RAG pipelines, semantic search indexes, or document similarity systems that need pay-per-use access without a subscription. The multilingual-e5-small model is well-suited for cross-lingual retrieval tasks. Prefer alternatives if you need larger embedding dimensions (e.g. 1536+) for higher-fidelity semantic tasks.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:31:37.811Z","isFirstParty":false}