Nataris — use P2P Android inference as a backend for your Flowise flows

[Sharrmavishal]

Built this over the past three months with a two-person team. Since Flowise supports ChatOpenAI with a custom base path, you can point it at Nataris and use P2P Android inference in your flows.

What Nataris is

A P2P inference marketplace. Android phones run open-weight models locally (Qwen 2.5 0.5B, Llama 3.2 1B) and serve requests via a standard OpenAI-compatible API. Phone owners earn per token. Developers get inference without managing any infrastructure.

No prompt logging. No content filtering. No model training on your queries.

Using with Flowise

In any ChatOpenAI node, set:

• Base Path: https://api.nataris.ai/v1
• Model Name: nataris-fast (Qwen 2.5 0.5B) or nataris-balanced (Llama 3.2 1B)
• API Key: your Nataris API key

Enables streaming in the node settings — mobile cold-starts can timeout on non-streaming requests.

Where we are

21 provider devices on the network, 2,775 inference jobs completed, 350K+ tokens processed during closed beta. Android app just went live on Google Play.

Good fit for flows where 5–20s latency is acceptable and privacy matters (no prompt logging at the API layer).

$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