🧠

DIGESTS

digests.4bots.ai

PDFs, reports, and filings → structured summary at your target token budget. NI 43-101 reports, SEDAR filings, press releases — compressed by GX10 and served as clean markdown + extracted fields.

Live Free — 5/day GX10-Powered x402 Native MCP Compatible

Long docs. Short summary. Your token budget.

Your agent needs to understand a 50-page NI 43-101 technical report or a 200-page SEDAR filing. DIGESTS compresses it to your target token budget — 200, 500, 2000, or full. Free tier: URL input only, 10-page limit. Paid: raw text upload, 100 pages, JSON field extraction.

📄 PDF → Markdown

Upload a URL or raw text. We extract the content (pdfplumber / pymupdf), then GX10 compresses it to your token budget. Structured markdown output.

🎯 Token budgets

Target 200, 500, 2000, or full. Agent picks the budget that fits its context window. Paid tier unlocks all 4 budgets.

🔬 Field extraction

Paid tier extracts structured fields: property name, commodity, measured + indicated ounces, inferred ounces. Output as JSON alongside the markdown summary.

🧠 GX10-powered

Local GX10 (Blackwell) handles abstractive compression. 50x faster than cloud APIs. Degraded mode available with basic extraction if GX10 is down.

One POST. Compressed output.

POST /v1/digests/compress

Compress a document by URL or raw text. Free: URL only, 10 pages, default budget. Paid: URL + raw text, 100 pages, all budgets, JSON fields.

curl -X POST "https://digests.4bots.ai/v1/digests/compress" \
  -H "Content-Type: application/json" \
  -d '{"url": "https://sedarplus.com/.../43-101-report.pdf", "budget_tokens": 2000, "style": "technical"}'

Example response:

{
  "url": "https://sedarplus.com/.../43-101-report.pdf",
  "title": "NI 43-101 Technical Report — Elk Gold Project",
  "compressed_markdown": "## Property Description\n...\n\n## Mineral Resources\n...",
  "token_count": 1847,
  "original_estimated_tokens": 45000,
  "compression_ratio": "96%",
  "fields": {
    "property": "Elk Gold Project",
    "commodity": ["gold"],
    "location": "BC, Canada",
    "measured_and_indicated_ounces": 125000,
    "inferred_ounces": 45000
  }
}

GET /health

Health check. Always free, always returns 200.

curl "https://digests.4bots.ai/health"

Free for light use. $0.005 per doc for power users.

Free tier covers 5 documents/day (10 pages max). Paid tier unlocks 100-page documents, all token budgets, and structured field extraction.

Free
$0 / month
No wallet required
  • 5 documents / day
  • URL input only
  • 10-page limit
  • Default token budget
  • Markdown output
Paid
$0.005 / document
via x402 USDC on Base
  • 200 documents / day
  • URL + raw text upload
  • 100-page limit
  • All token budgets
  • JSON field extraction

Compress your next 43-101 report.

No signup. No API key. Just send a request.

How x402 works