{"uid":"cap_ij5XuGZgefVmO2IYicniR","slug":"private-llm-embeddings-a7ace790","name":"Private LLM Embeddings","description":"Privacy-first OpenAI-compatible text embeddings (768 dims) from a local encoder on dedicated hardware - your text never reaches a third-party cloud. Send {\"input\": string or array of up to 64 texts}; receive standard OpenAI embeddings JSON with usage. Built for RAG, semantic search, dedupe and clustering in agent pipelines. ~2,000-token limit per text. Pay per call in USDC on Base (x402), no API key or account.","url":"https://api.erb-llm.com/v1/embeddings?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"input":{"type":"array","items":{"type":"string"},"description":"One or more texts to embed (a single string also works). Keep each text under ~2,000 tokens; batches above 64 texts are clamped to the first 64 (never rejected after paying)."},"model":{"type":"string","description":"Optional. Default: the gateway's local embedding model (nomic-embed-text-v1.5)."}}},"responseSchema":null,"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_Ae5lp4TEO6X2wfmzywNQI","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":"Generates OpenAI-compatible 768-dimensional text embeddings from a private self-hosted encoder, paid per call in USDC via x402 with no API key required.","exampleAgentPrompt":"Embed these 10 product description strings into vectors using the private local encoder at erb-llm.com — I need 768-dim OpenAI-format embeddings for a semantic search index, and I'll pay per call in USDC.","exampleUseCases":[{"title":"RAG pipeline document indexing","prompt":"Take these 50 chunked paragraphs from my internal policy docs and embed them all using the private erb-llm encoder — I need 768-dim vectors I can store in my vector DB for RAG retrieval, without sending anything to OpenAI."},{"title":"Semantic deduplication of user records","prompt":"I have a list of 64 customer support tickets — can you embed all of them with the private self-hosted embedding model and return the vectors so I can cluster and remove near-duplicate tickets?"},{"title":"Private semantic search over sensitive data","prompt":"Embed this query — 'quarterly revenue projections for EMEA' — using the local private encoder so I can run a cosine similarity search against our confidential finance document index without any data leaving our control."}],"resultDescription":"Returns a standard OpenAI embeddings response JSON containing an array of embedding objects (each with a 768-dimensional float vector, index, and object type), plus a usage object with prompt_token_count and total_tokens. Compatible with any OpenAI embeddings client library.","failureModes":["Input batch exceeds 64 texts — clamped silently to first 64 (no error, but caller may not notice truncation)","Individual text exceeds ~2,000 token limit — may be truncated or rejected depending on model behavior","Payment failure via x402 — call not executed, payment-related error returned","Malformed input (non-string array items) — likely 422 or 400 error","Model unavailable due to self-hosted infrastructure downtime — 503 or timeout"],"whenToPreferThis":"Choose this endpoint when privacy is a priority and you cannot send text to third-party cloud APIs like OpenAI or Cohere. Ideal for agent pipelines doing RAG, semantic search, deduplication, or clustering where data sensitivity prevents use of hosted embedding services. Also preferred when you want pay-per-call USDC pricing via x402 with no account signup, API key management, or monthly subscription. Best for batches of up to 64 texts under ~2,000 tokens each.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T20:32:39.058Z","isFirstParty":false,"canonicalSlug":"private-llm-embeddings-a7ace790"}