# 24K Labs AI Document Extraction

> 24K Labs AI Document Extraction is a paid API for AI agents from api.24klabs.ai, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Extracts structured information (titles, decisions, action items) from document text using Claude AI, paid per-request in USDC on Base L2

## Facts

- Endpoint: POST https://api.24klabs.ai/api/extract-document
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/24k-labs-ai-document-extraction-e5a8850b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WJB-Dw-FKjIbPH8HbH_VI

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 24k-labs-ai-document-extraction-e5a8850b -d '<json body>'
```

Example prompt: Can you extract the key information from these meeting notes — pull out the title, any decisions made, and who's responsible for what actions: 'Team synced on Q3 roadmap. Decided to ship v2 by Friday. Sean will update the docs, Maria will notify stakeholders.'

## When to prefer this

Use this endpoint when you need lightweight, pay-per-use AI document extraction without managing API keys or subscriptions. Ideal for agents that occasionally need to parse meeting notes, contracts, or freeform text into structured fields using Claude, and want to pay only for what they use in USDC on Base L2.

## Known failure modes

- Empty or missing 'code' field returns an error or empty extraction
- Document text too long may exceed token limits
- Ambiguous or unstructured input may produce incomplete extractions
- Network or payment failure on Base L2 returns HTTP 402 if USDC payment cannot be processed
- Malformed JSON request body returns 400 error

## How this service works

A curated directory of x402 services — each one on the list on purpose, with the health, uptime, and independent trust grades from across the ecosystem gathered in one place.

## Output

A JSON object containing the model used (claude-haiku-4-5), a formatted markdown-style result string with extracted fields like Title, Decisions, and Action Items, and the number of tokens consumed by the request.

## Example request

```json
{
 "code": "Team synced on Q3 roadmap. Decided to ship v2 by Friday. Sean will update the docs, Maria will notify stakeholders.",
 "context": "Extract title, decisions, and action items from meeting notes",
 "language": "text"
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "code": {
   "type": "string",
   "description": "Primary input content"
  },
  "context": {
   "type": "string",
   "description": "Optional context or instructions"
  },
  "language": {
   "type": "string",
   "description": "Programming language (code services)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "claude-haiku-4-5",
  "result": "**Title:** Meeting Notes\n**Decisions:** Ship v2 by Friday\n**Actions:** Sean: update docs",
  "tokens_used": 160
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/24k-labs-ai-document-extraction-e5a8850b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.24klabs.ai](https://www.zero.xyz/host/api.24klabs.ai/llms.txt)