Skip to content
Price
Agents pay the catalog list in USDC. That is credits × $0.001 at Entry. Humans who buy a volume pack burn the same credits cheaper. Volume, not a second price list.
Protocol · x402 · USDC
How agents pay.
Every live per-call product in the catalog is callable without an account. Read the manifest, settle in USDC on Base or Solana, receive structured JSON inline.
Integration spec
Manifest/.well-known/agent-manifest.json
MCPdod.hshintelligence.com/mcp
Protocolx402
Asset / chainsUSDC · Base, Solana
The contract
One manifest. Tools, prices, rails, schemas.
The 18 live per-call products live in the catalog. This page is the payment contract, how an agent discovers a tool, pays list, and consumes the JSON. Quoted jobs are not on this rail.
- 01
Find
GET /.well-known/agent-manifest.json. Product ids, unit prices, MCP URL, settlement rails.
- 02
Select
Each live product is a tool. Example: hsh-crypto-intel with {"symbol":"BTCUSDT"}.
- 03
Pay
x402 payment payload in USDC on Base or Solana. Send it in X-Payment.
- 04
Consume
POST to dod.hshintelligence.com/mcp. Structured JSON. Settlement on-chain.
curl
# 1. Read the manifest
curl -s https://hshintelligence.com/.well-known/agent-manifest.json
# 2. Call MCP with an x402 payment payload on Base or Solana (USDC)
curl -s https://dod.hshintelligence.com/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json" \
-H "X-Payment: <x402-usdc-base-payload>" \
-d '{"tool":"hsh-crypto-intel","input":{"symbol":"BTCUSDT"}}'Integration spec
Settlement
List price, per call. No account.
Rails
USDC on Base and Solana. Attach the x402 payload. No API key, no balance, no signup.
Out of scope
Contact files, extraction jobs, monitoring, and custom cuts are quoted per job. Fine-tuning datasets settle on this rail via hsh-finetune-dataset.
Different product
Not a live JSON call. A HuggingFace dataset job, paid in USDC, delivered as a repo.
Fine-tuning
For autonomous agents
Buy a fine-tuning dataset programmatically.
The hsh-finetune-dataset tool is live in the DOD catalog. Your agent describes the task, pays per-tier in USDC via x402, and receives an answer-verified, HuggingFace-ready dataset. Same product as the human page, callable end to end.
MCP endpoint · live tool
https://dod.hshintelligence.com/mcp
x402 resource
/x402/t/hsh-finetune-dataset
USDC on Base or Solana · from $75
- 01
Call the hsh-finetune-dataset tool
Discover it via MCP at the endpoint above, or hit the x402 resource directly. The tool is live now and listed in the DOD catalog. Describe the task in plain language, what the model should learn to do, plus the row count and, optionally, the platform you will train on.
POST /x402/t/hsh-finetune-datasetPOST /x402/t/hsh-finetune-dataset { "task_description": "step-by-step math word-problem reasoning with verified answers", "domain": "math", "row_count": 3000, "target_platform": "gradients", "verification": "programmatic" } - 02
Pay per the tier in USDC via x402
Pricing is by row count: 1–2K rows $75 · 2–5K $150 · 5–10K $300. Larger cuts are scoped on request. Settle over x402 on Base mainnet or Solana. The catalog entry carries both payment rails. No card, no account, no form.
- 03
Receive an order reference and tracking
The tool returns an order reference and a track URL. The dataset is built and answer-verified. Every checkable answer is confirmed in code, deduplicated, and split train / val / test. Delivery is async. Poll the track URL for status.
response{ "ok": true, "order": { "reference": "HSH-XXXXXXXX", "track_url": "https://dod.hshintelligence.com/track/HSH-XXXXXXXX" } } - 04
Get a HuggingFace-ready repo
Delivered in Alpaca schema (instruction / input / output) by default. Drop it straight into Gradients (SN56), TRL, Axolotl, or Unsloth. See a live verified sample before you buy.
Live verified sample
Back to fine-tuning datasets