Back to Browse
ManyLives AI Rerank
x402
ManyLives AI Rerank is a paid API for AI agents from api.manylives.me, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-10).
Reranks a list of text documents by relevance to a given query using a BGE reranker model, returning scored and sorted results.
Price / call$0.003
Success—
StatusUnknown
How this service works
Pay-per-call tools for people building AI agents: live web search and page contents, point-in-time crypto market data and news for backtests (no lookahead), verifiable track records of 1,000 crypto strategies locked on the Base network, company profiles, quick AI and batch prices. Ask us to turn a public website into a JSON endpoint. Pay per call, no account, free trial.
Output
Returns a JSON object containing the model name (bge-reranker-base), the original query, and a results array where each item includes the document text, its original index in the input array, and a float relevance score. Results are ordered from most to least relevant.
Example use cases
RAG pipeline passage reranking
“I've retrieved 20 chunks from my knowledge base for the question 'what is the refund policy?' — can you rerank them by relevance and give me the top 5 so I only send the most useful context to my LLM?”
Candidate answer scoring for QA
“Score each of these 8 candidate answers against the question 'how does Base network settle transactions?' and tell me which one is most relevant with its confidence score.”
Agent-to-agent tool selection
“I have a list of 15 agent tool descriptions and a user request 'find me the current Bitcoin price' — rerank the tools by how well they match that request so I can pick the right one to call.”
Technical details
Endpoint
POSThttps://api.manylives.me/paid/ai/rerank?utm_source=zero.xyzWhen to prefer
Choose this endpoint when you need a lightweight, pay-per-call semantic reranker without committing to a subscription — ideal for RAG pipelines, agentic tool selection, or QA systems that need to prioritize a short list of retrieved passages. It is especially useful for AI agents operating on the Base network that already handle x402 micropayments. Prefer this over full embedding-search stacks when you already have a candidate set and just need relevance ordering.
Side effects
- Missing required 'query' field returns a validation error
- Missing required 'documents' field returns a validation error
- Exceeding 50 documents in the array may be rejected
- Documents exceeding 4,000 characters each may be truncated or rejected
- Insufficient USDC balance or failed x402 payment returns a 402 Payment Required response
- Malformed JSON body returns a 400 error
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| query | string | the question (required) |
| top_n | string | optional, how many to return (default all) |
| documents | string | array of strings (required, max 50, each up to 4,000 characters) |
Output
Schema · Response
{
"type": "json",
"example": {
"model": "bge-reranker-base",
"query": "how do agents pay per call?",
"results": [
{
"text": "Agents pay per request with a signed stablecoin authorisation.",
"index": 1,
"score": 0.0415
},
{
"text": "The weather in Sydney is mild today.",
"index": 0,
"score": 0
}
]
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"