# 24K Labs Document Extraction API

> 24K Labs Document Extraction API 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 with USDC on Base L2

## Facts

- Endpoint: POST https://api.24klabs.ai/api/v1/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-document-extraction-api-3bca23b9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YmrRtp6JlVTZCvLSKLJit

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-document-extraction-api-3bca23b9 -d '<json body>'
```

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

## When to prefer this

Choose this endpoint when you need lightweight, pay-per-request AI document extraction without committing to a subscription or managing API keys — ideal for sporadic or low-volume document parsing tasks billed in USDC on Base L2

## Known failure modes

- Empty or missing 'code' field returns an error or empty result
- Document too long may exceed token limits and return a truncated or failed response
- Payment not included or insufficient USDC causes a 402 Payment Required response
- Malformed JSON input returns a 400 error
- Service temporarily unavailable returns a 5xx error

## How this service works

Extract and structure key information from any document.

## Output

Returns a JSON object with the AI model used (claude-haiku-4-5), a structured markdown-formatted result containing extracted fields like title, decisions, and action items, and the number of tokens consumed

## Example request

```json
{
 "code": "Team meeting notes from Q3 planning session. Attendees: John, Sarah, Mike. Title: Q3 Roadmap Review. Key decisions: (1) Approved budget increase for infrastructure, (2) Decided to prioritize mobile app redesign. Action items: John to prepare detailed budget breakdown by Friday, Sarah to schedule stakeholder meetings next week, Mike to create technical specifications for mobile redesign.",
 "context": "Extract title, decisions, and action items from these 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-document-extraction-api-3bca23b9/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)