# Venice AI Text Parser

> Venice AI Text Parser is a paid API for AI agents from api.venice.ai, paid per call via x402, $10/call, status unknown (last checked 2026-10-10).

Extracts text content and token count from uploaded document files (PDF, DOCX, PPTX, XLSX, plain text) with zero data retention

## Facts

- Endpoint: POST https://api.venice.ai/api/v1/augment/text-parser?utm_source=zero.xyz
- Price: $10/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402, ai_ml
- Canonical page: https://www.zero.xyz/c/venice-ai-text-parser-84342fe0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_VW04Rswrc4OntF5yEH4CK

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 venice-ai-text-parser-84342fe0 -d '<json body>'
```

Example prompt: Can you extract all the text from this PDF report I'm uploading? Give me back the text and let me know how many tokens it is.

## When to prefer this

Choose this endpoint when you need to extract plain text from structured document formats (PDF, DOCX, PPTX, XLSX) to feed into downstream NLP pipelines, LLM prompts, or search indexes. Prefer it over general-purpose OCR when working with text-based documents rather than scanned images. Strong choice when privacy matters, since documents are processed entirely in-memory with zero retention.

## Known failure modes

- File exceeds 25MB limit — request rejected
- Unsupported file format submitted — parsing fails
- Malformed or corrupted document — extraction error returned
- Insufficient x402 wallet balance — 402 Payment Required with top-up instructions
- Invalid or missing API key — 401 Unauthorized
- File field missing from multipart form — validation error

## How this service works

Extracts text from a document file. Supports PDF, DOCX, PPTX, XLSX, and plain text formats. Upload a file via multipart/form-data.

**Privacy:** Text parsing runs entirely in-memory on Venice's infrastructure with zero data retention. Documents are processed and immediately discarded — no content is stored or logged.

**Authentication:** This endpoint accepts either a Bearer API key or an `X-Sign-In-With-X` header for x402 wallet-based authentication. When using x402, a `402 Payment Required` response indicates insufficient balance and includes top-up instructions.

## Output

Returns a JSON object containing the full extracted text from the document as a string and the token count of that text as a number. Alternatively, if response_format is set to 'text', returns just the raw extracted text string.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "file"
 ],
 "properties": {
  "file": {
   "type": "string",
   "format": "binary",
   "description": "The document file to parse. Supported formats: PDF, DOCX, PPTX, XLSX, and plain text files. Maximum size: 25MB."
  },
  "response_format": {
   "enum": [
    "json",
    "text"
   ],
   "type": "string",
   "default": "json",
   "description": "The format of the response output. \"json\" returns structured JSON with text and token count, \"text\" returns only the extracted text."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text",
  "tokens"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "The extracted text content from the document."
  },
  "tokens": {
   "type": "number",
   "description": "The token count of the extracted text."
  }
 },
 "description": "Text parser response containing extracted text and token count."
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/venice-ai-text-parser-84342fe0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.venice.ai](https://www.zero.xyz/host/api.venice.ai/llms.txt)