{"uid":"cap_0ZrcDVYWcHHt_GaI4b7JB","slug":"bge-m3-multilingual-text-embedding-and-semantic-ranking-api-f4fa4e4c","name":"BGE-M3 Multilingual Text Embedding and Semantic Ranking API","description":"Generate an AI_POLICY.md and a pull request template with an AI-disclosure section for your open-source repo. Free, runs in your browser.","url":"https://ai-policy-kit.moneymaker-ai.workers.dev/api/ai/embed?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["texts"],"properties":{"query":{"type":"string","description":"optional; rank texts against it"},"texts":{"type":"array","items":{"type":"string"},"description":"1-32 strings (or text= for one)"},"include_vectors":{"enum":["true","false"],"type":"string"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"note":"bge-m3 dense vectors (multilingual). With query=, ranking is cosine similarity computed by us. Vectors from other models are not comparable.","count":3,"model":"@cf/baai/bge-m3","ranking":[{"index":0,"score":0.64282,"preview":"USDC is a dollar stablecoin."},{"index":2,"score":0.59885,"preview":"Base is an Ethereum L2."},{"index":1,"score":0.32354,"preview":"The cat sat on the mat."}],"dimensions":1024,"embeddings":[[-0.029053,0.002089,-0.061401,0.005913,"…1020 more"],[-0.011223,0.025696,-0.084412,-0.002304,"…1020 more"],[0.009056,0.014679,-0.021378,0.038177,"…1020 more"]],"normalized":false,"neurons_estimated":0.54}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0005","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":"$0.0005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ofrj6XUyn_iTV143sTNJx","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates dense 1024-dimensional multilingual embeddings using BGE-M3 and optionally ranks input texts by cosine similarity against a query.","exampleAgentPrompt":"I have these three passages — 'USDC is a dollar stablecoin', 'Base is an Ethereum L2', and 'The cat sat on the mat' — can you embed them and rank them by how relevant they are to the query 'what is crypto'?","exampleUseCases":[{"title":"Semantic search over knowledge base","prompt":"I have a list of 20 FAQ answers and a user's question 'how do I reset my password' — embed all of them and tell me which FAQ answer is most relevant to the question."},{"title":"Multilingual document similarity ranking","prompt":"Here are five product descriptions in mixed English and Spanish — embed them all and rank them by similarity to the query 'wireless noise-cancelling headphones'."},{"title":"Vectorize texts for storage in vector DB","prompt":"Take these 10 customer review sentences and generate BGE-M3 embeddings for each one so I can store the vectors in my Pinecone index — I want the raw 1024-dimensional vectors back, not just the rankings."}],"resultDescription":"Returns a JSON object with: BGE-M3 dense embeddings (1024-dimensional float arrays) for each input text, an optional ranked list of texts with cosine similarity scores if a query was provided, the model name, total count, and vector dimensions. Normalized flag and neuron cost estimate are also included.","failureModes":["Missing required 'texts' query parameter returns an error","More than 32 strings submitted exceeds the input limit","Empty string array causes a processing error","Network timeout on very large batch inputs","Malformed query parameter format returns a 400 error"],"whenToPreferThis":"Choose this endpoint when you need multilingual semantic embeddings using the BGE-M3 model specifically, or when you want server-side cosine similarity ranking computed for you without managing a vector database. It is ideal for lightweight, stateless embedding tasks where you want both vectors and ranking in a single API call at very low cost.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-30T19:03:34.940Z","isFirstParty":false,"canonicalSlug":"bge-m3-multilingual-text-embedding-and-semantic-ranking-api-f4fa4e4c"}