{"uid":"cap_CbYngl-mryZRXV2tc3x9_","slug":"perplexity-embed-1ac0164d","name":"Perplexity Embed","description":"Generate vector embeddings for semantic search, clustering, and RAG. Supports MRL (Matryoshka) dimensionality reduction and INT8/BINARY quantization.","url":"https://perplexity.mpp.paywithlocus.com/perplexity/embed?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["model","input"],"properties":{"input":{"anyOf":[{"type":"string"},{"type":"array","items":{"type":"string"}}],"description":"Text to embed. Single string or array of strings."},"model":{"type":"string","description":"Embedding model: 'pplx-embed-v1-0.6b' or 'pplx-embed-v1-4b'"}},"additionalProperties":true},"responseSchema":null,"example":{"request":{"input":"The quick brown fox jumps over the lazy dog.","model":"pplx-embed-v1-4b"},"response":{"data":{"data":[{"index":0,"object":"embedding","embedding":"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"}],"model":"pplx-embed-v1-4b","usage":{"cost":{"currency":"USD","input_cost":3e-7,"total_cost":3e-7},"total_tokens":10,"prompt_tokens":10},"object":"list"},"success":true}},"exampleRequest":{"input":"The quick brown fox jumps over the lazy dog.","model":"pplx-embed-v1-4b"},"tags":["search","ai-search","web-grounding","sonar","ai"],"displayCostAmount":"0.001","displayCostAsset":"USDC","priceDynamic":true,"priceHint":"~$0.001","priceStatus":"priced","priceSource":"settled","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":"dynamic","summary":"~$0.001 (dynamic)","primary":{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"},"accepted":[{"kind":"dynamic","protocol":"mpp","network":"tempo","amountUsd":"0.001","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_svIcPjXIgyTk3iX6ASpou","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.001","costPer":"request","priority":0,"asset":"0x20c000000000000000000000b9537d11c60e8b50","unit":"request","depositMicros":null,"planRef":null}],"brandName":"Perplexity","brandSlug":"perplexity","brandBaseUrl":"https://perplexity.ai","brandDocsUrl":"https://docs.perplexity.ai","whatItDoes":"Converts text into dense vector embeddings using Perplexity's pplx-embed-v1 models (0.6B or 4B parameter variants)","exampleAgentPrompt":"Use Perplexity's pplx-embed-v1-4b model to embed this text so I can store it in my vector database: 'Quantum computing leverages superposition and entanglement to perform calculations exponentially faster than classical computers.'","exampleUseCases":[{"title":"Build semantic search for knowledge base","prompt":"I need to embed all my company's support documents so customers can find answers by describing their problem in natural language instead of searching for keywords."},{"title":"Create similarity matching for customer queries","prompt":"Help me convert incoming customer questions into embeddings and find the most similar ones from our FAQ database to auto-suggest relevant answers."},{"title":"Index product catalog for vector search","prompt":"Can you embed all our product descriptions using Perplexity's model so I can build a neural search engine that understands what customers mean, not just what they type?"}],"resultDescription":"A dense floating-point embedding vector representing the semantic content of the input text, produced by the specified pplx-embed-v1 model (0.6B or 4B). The vector can be used for downstream tasks like similarity search, clustering, or retrieval.","failureModes":["Invalid model name — must be 'pplx-embed-v1-0.6b' or 'pplx-embed-v1-4b'","Missing required 'input' field returns validation error","Input text exceeds model context window","Authentication or payment failure returns 401/402","Empty string input may return error or zero vector"],"whenToPreferThis":"Choose this endpoint when you need fast, high-quality text embeddings from Perplexity's purpose-built embed models (pplx-embed-v1). Prefer the 4B variant for higher fidelity semantic representations and the 0.6B variant for speed-sensitive or cost-sensitive workloads. Well-suited for building RAG pipelines alongside Perplexity's Sonar chat and search endpoints.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-09T18:31:28.252Z","isFirstParty":false,"canonicalSlug":"perplexity-embed-1ac0164d"}