Getting started
Quickstart
Three ways in: use the network, verify the claims yourself, or contribute compute and earn.
Call the API
The inference endpoint is OpenAI-compatible, so most existing SDKs and tools work by changing the base URL. Prompts are billed in tokens and are not attached to a profile.
curl https://api.noviqai.xyz/v1/chat/completions \
-H "Authorization: Bearer $NOVIQ_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "noviq-max-27b",
"messages": [{ "role": "user", "content": "Explain private inference." }]
}'Models
noviq-max-27b); in-browser WebGPU workers advertise lighter ones (for example noviq-browser-8b). Availability depends on who is online in the swarm.Run the proof gates
The privacy and correctness claims are not asks for trust - they run on CPU in seconds. Clone the research repo and run the gates yourself.
git clone https://github.com/Noviqai-xyz/noviq_swarm
cd noviq_swarm
python3.12 -m venv .venv
.venv/bin/pip install torch cryptography numpy
# Gate A - the split run is bit-identical to the whole model
.venv/bin/python -m proof.correctness_gate
# Gate D - a reconstruction adversary drops from ~100% to near chance
.venv/bin/python -m proof.obfuscation_gateWhat you should see
Contribute a GPU
A worker is a small client that connects to the orchestrator over a WebSocket and serves inference jobs. There are two ways to run one:
- Native. Point the worker at a local Ollama install with a capable model. Best throughput, best earnings.
- Browser. Open the
/earnpage on a WebGPU-capable browser and it becomes a worker with zero install.
See Workers and earning for setup, model classes, and how payouts work.
Stake $NOVIQ
If you would rather back the network than run it, stake $NOVIQ from self-custody and earn a share of real network revenue. Only your wallet can unstake or claim. See Staking and treasury.
