Nataris — P2P inference network with no prompt logging, no content filtering, works as an OpenAI-compatible API

[Sharrmavishal]

Built this over the past three months with a two-person team. The PrivateGPT community feels like the right place to share it — you're all here because you care about keeping your data out of corporate pipelines, which is exactly what Nataris is about.

What Nataris is

A P2P inference marketplace. Android phones run open-weight models on-device (Qwen 2.5 0.5B, Llama 3.2 1B) and serve API requests through a standard OpenAI-compatible endpoint. Phone owners get paid per token. Developers get inference without managing any servers.

No prompt logging. No content filtering. No model training on your queries. The inference never touches a datacenter we own.

How it works

Point any OpenAI-compatible client at https://api.nataris.ai/v1 with your API key. The request gets routed to a provider device, runs on-device via llama.cpp, and streams back the response.

Model aliases:

• nataris-fast — Qwen 2.5 0.5B (~5s)
• nataris-balanced — Llama 3.2 1B (~15-20s)

Keep streaming enabled — cold starts on mobile devices mean non-streaming requests can timeout.

How it compares to PrivateGPT

Different use cases — PrivateGPT is for running everything locally on your own machine. Nataris is for when you want the same privacy guarantees (no corporate logging, no content filtering) but don't want to manage local hardware or need an API for an app/integration. Think of it as the hosted alternative that still doesn't log your prompts.

Where we are

21 provider devices live on the network, 2,775 inference jobs completed, 350K+ tokens processed. Just came out of closed beta. Android provider app is live on Google Play.

$5 free credits on signup, no card needed.

API: https://api.nataris.ai/v1
Docs: https://api.nataris.ai/docs
Provider app (earn by running models on your Android): https://play.google.com/store/apps/details?id=ai.nataris.app