{"uid":"cap_4KrnJT4BJqrMm5USutD3L","slug":"agentrxi-rerank-8b58294c","name":"AgentRXI Rerank","description":"Rerank up to 100 documents by relevance to a query (BGE reranker). Returns indices and scores, best first. Drop-in step for RAG and search pipelines. Also callable as GET with the same fields as query parameters.","url":"https://agentrxi.com/v1/rerank?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":["query","documents"],"properties":{"query":{"type":"string"},"top_k":{"type":"integer"},"documents":{"type":"string","description":"separate items with |"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_3gAkc215To70T4AMsgS3Y","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Reranks up to 100 documents by relevance to a query using BGE reranker, returning sorted indices and scores best-first.","exampleAgentPrompt":"Rerank these 5 passages by how relevant they are to the question 'What causes inflation?' and give me the top 3: 'Central banks raise interest rates to fight inflation | Supply chain disruptions raise prices | Inflation is measured by CPI | Governments print money to fund deficits | Stock markets reflect economic sentiment'.","exampleUseCases":[{"title":"RAG pipeline relevance boost","prompt":"I've retrieved 20 chunks from my vector database for the question 'How do transformers handle long-range dependencies?' — can you rerank them by relevance and give me the top 5 so I only pass the best context to the LLM?"},{"title":"Search result reordering","prompt":"I got 15 organic search results for 'best practices for Kubernetes security' — rerank them by how closely each title and snippet actually matches that topic and show me the top 10 in order."},{"title":"FAQ matching for support bot","prompt":"I have a user question 'Why was I charged twice?' and 30 FAQ entries — use the BGE reranker to score each FAQ by relevance to that question and return the top 3 best matches."}],"resultDescription":"An ordered list of results, best-first, each containing the original document index and a relevance score (float). The top_k parameter controls how many results are returned. Agents can use these indices to reorder their original document list.","failureModes":["Missing required 'query' or 'documents' parameters returns a 400 error","Documents list exceeds 100 items may be rejected or truncated","Pipe delimiter not used correctly in GET query parameter causes parsing errors","Empty documents list or empty query string returns an error","Payment not included or invalid causes 402 Payment Required response"],"whenToPreferThis":"Use this endpoint when you need a fast, pay-per-call reranking step in a RAG or hybrid search pipeline and don't want to self-host a reranker model. Prefer it over embedding-similarity-only ranking when result precision matters more than recall. The BGE reranker is a strong cross-encoder that outperforms cosine similarity for relevance scoring. At $0.003 per call it's cost-effective for up to 100 documents per request.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T06:39:07.894Z","isFirstParty":false,"canonicalSlug":"agentrxi-rerank-8b58294c"}