NVDC

decentralized inference network

connecting…

Use the network — OpenAI-compatible API

Point any OpenAI client at the NVDC coordinator. Requests are routed to a miner serving your chosen model and streamed back.

Base URL—

Market price (selected model)—

Model Min rating Max price (USD/Mtok) Pin miner

Example (Python)

—

Example (curl)

—

Model Min rating Max price Pin miner

Wallet—

NVDC network status

miners online

attested

cumulative RAM

requests in flight

Models on the network

Model	Miners	Market price (USD/Mtok)	Avg tokens/sec

Miners

Name	Model	Price	Accel	RAM	Rating	Success	TPS	Queue	Earned	Attested

Ledger — dual-signed inference receipts (metadata only — prompts/responses are committed as hashes, never shown; click a receipt to re-verify)

Time	Model	Miner	Tokens	Cost	Delivery	Signatures	Receipt

—

node status

Offline

Inference mechanism

Accelerator—

Type—

GPUs—

Memory budget—

System RAM—

Platform—

Trust & status

Attestation—

Ollama runtime—

Active modelnone

Hot in memory—

Network—

Go live on the network

Pricing — your minimum USD per 1M tokens

Min price (USD / 1M tokens)

When a consumer sets a max price at or above your minimum, you're paid their max — you keep the surplus.

Choose one model to serve — your node commits to a single hot-loaded model, like a miner choosing one algorithm.

USD balance

0.00 USD

$0.00

earned through mining

$0.00

spent on inference

Add funds

Amount (USD)

Prepaid credits via Stripe. Per-request cost is sub-cent, so you top up a balance and spend it down.

Miner payouts — withdraw mining earnings

Connect a Stripe account to withdraw your balance to your bank.

Your clusters & machines — every client linked to this account

Your transactions

Time	Type	Model	Tokens	Amount (USD)	Delivery