CHUNKER.CC // x402 Protocol

System.Demo

📁

DROP FILE OR CLICK TO UPLOAD

[SUPPORTED: PDF, DOCX, TXT, RTF, HTML, MD]

PAYMENT REQUIRED

$0.001

1000 USDC micro-units

WALLET NOT CONNECTED

Network: SOLANA-MAINNET

System.Benefits

⚡ ZERO_SETUP

No libraries to install. No Docker containers. No infrastructure. Just hit the API and get chunks. Agents can discover and use us autonomously.

💰 MICROPAYMENTS

Pay only for what you use via x402 protocol. No subscriptions. No monthly fees. $0.0001 to start. Cash-flow positive from transaction #1.

🧠 CONTEXT_INJECTION

Our Tier 3 solves the "who is 'He'?" problem. We inject document context and entity metadata so your AI never loses the thread. No open-source tool does this.

⚡ INSTANT_RESPONSE

Millisecond latency. No 30-second LLM context loading. Get your chunks immediately and move on. Built for real-time agentic workflows.

System.Info

>> We built CHUNKER.CC for the Agentic Economy. In 2026, AI agents have wallets and make autonomous decisions. They don't "install Haystack" or "sign up for a SaaS plan." They find a service, pay $0.001 via x402, and get results instantly.

>> The problem we solve: Context Window Limits. When an agent hits a 500-page PDF but only has 8K tokens of memory, it needs smart chunking. Our Tier 3 contextual enrichment ensures the agent never loses track of "who," "what," or "when."

>> Built on Solana for near-zero transaction fees. Powered by x402 V2 for internet-native payments. Designed for autonomous agents, not humans clicking buttons.

Competitive.Edge

vs. GEMINI

99.75%

CHEAPER

$0.001 vs $2-4 per doc

vs. HAYSTACK

0 MIN

SETUP TIME

No 2-4hr infrastructure setup

vs. FIRECRAWL

CONTEXT

PRESERVATION

They scrape. We understand.

[TECHNICAL_ADVANTAGE] → Our contextual injection solves the pronoun resolution problem. When your chunk says "He died in 1867," we prepend: [Referring to: Sir John A. Macdonald]. Open-source tokenizers can't do this. Gemini long-context is too expensive. We're the sweet spot.

Pricing.Matrix

TIER_1: DEMO

FREE

Recursive character splitting
Up to 100 pages/day
Basic paragraph detection
Quality: 6/10

TIER_2: STANDARD

$0.001/page

Sentence-aware chunking
Semantic boundary analysis
Header recognition
Quality: 7.5/10 ⭐ RECOMMENDED

TIER_3: PROFESSIONAL

$0.008/page

Context injection
Entity extraction
Gemini-validated quality
Quality: 9.0/10

Integration.Protocol

# Demo tier (FREE - no payment required)

curl -X POST https://api.adepti.cc/chunk/demo \

  -F "file=@document.txt"

# Paid tiers (include Solana TX signature)

curl -X POST https://api.adepti.cc/chunk/standard \

  -H "X-PAYMENT: <solana-tx-signature>" \

  -F "file=@document.txt"

// Browser: Connect Phantom, pay USDC, upload

const { signature } = await phantom.signAndSendTransaction(tx);

fetch('/chunk/standard', { headers: { 'X-PAYMENT': signature }, body: formData });

FAQ.Database

What is document chunking and why do I need it? [+]

Document chunking splits large documents into smaller, semantically meaningful pieces for AI processing. LLMs have context window limits (8K-128K tokens), so a 500-page PDF needs to be chunked before it can be searched or analyzed. Poor chunking = lost context = bad AI responses.

How does payment work? [+]

We accept USDC on Solana with two payment methods:

1. Manual (Web UI): Connect your Phantom wallet on this page, select a paid tier, and approve the USDC transfer. The transaction signature is automatically sent with your file.

2. Programmatic (x402 API): For AI agents and developers - call /estimate to get pricing, execute a USDC transfer on Solana, then include the TX signature in the X-PAYMENT header when calling the chunking endpoint.

Payment is per-page based on document size (~500 chars = 1 page). Demo tier is free (100 pages/day limit).

What's the difference between the tiers? [+]

Demo (Free): Basic character splitting. Good for testing.
Standard ($0.001/page): Sentence-aware chunking with semantic boundaries. Best for most use cases.
Professional ($0.008/page): Adds context injection and entity extraction. When a chunk mentions "He," we prepend who "He" refers to.

What file formats are supported? [+]

Currently: PDF and TXT files. PDFs must be text-based (not scanned images). We extract text and calculate pages at ~500 characters per page.

Can AI agents use this API autonomously? [+]

Yes! That's what we're built for. Agents can call /estimate to get pricing, execute a USDC transfer on Solana, then call the chunking endpoint with the TX signature in the X-PAYMENT header. Fully autonomous, no human intervention needed.

Is my data stored or logged? [+]

No. Documents are processed in memory and immediately discarded. We don't store your files, chunks, or content. Only basic request logs (IP, timestamp, file size) are kept for rate limiting and abuse prevention.