# AgentRAG Ingest

> AgentRAG Ingest is a paid API for AI agents from api.agentx402.ai, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Pre-warms the AgentRAG retrieval index by ingesting URLs, crawl roots, or raw text documents ahead of querying, or forces a refresh of already-indexed pages.

## Facts

- Endpoint: POST https://api.agentx402.ai/v1/rag/ingest
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrag-ingest-44cfd801
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_nVxQStstQYG_yWfo_C1bk

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentrag-ingest-44cfd801 -d '<json body>'
```

Example prompt: Index https://docs.myproduct.com as a crawl root in AgentRAG so I can query it later — crawl the whole same-origin site and make sure it's fresh.

## When to prefer this

Use this endpoint when you need to pre-populate or refresh the AgentRAG index before issuing queries — especially for raw text documents that have no URL (the only way to index plain text), for bulk crawl-based ingestion of a site, or when you want to guarantee fresh content. Prefer this over the query endpoint's inline indexing when you want explicit control over what's indexed, when ingestion latency should be decoupled from query latency, or when you want to take advantage of the prepay credit discount (20% off per-op price).

## Known failure modes

- Invalid or unreachable URL returns an error with no credits charged
- Raw text body missing or malformed causes a 400 validation error
- Insufficient prepaid credits results in a payment-required or 402 response
- Same-origin crawl exceeds page limit, partial ingestion returned
- Network timeout on large crawl roots may result in partial completion

## How this service works

Explicit pre-warm for AgentRAG over x402 — index URLs, same-origin crawl roots, or raw documents (text with no URL) ahead of querying, or force a refresh of already-indexed pages. The only way to index raw text directly. Ingest $0.005/page; prepay $1 = 10,000 credits, spent at 80% of the per-op price (20% off). Docs: https://agentx402.ai

## Output

Returns an ingestion confirmation indicating how many pages were indexed or refreshed, along with credit usage. Indexed content becomes available for retrieval via the AgentRAG query endpoint.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "properties": {}
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrag-ingest-44cfd801/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.agentx402.ai](https://www.zero.xyz/host/api.agentx402.ai/llms.txt)