NeuralGate Documentation
NeuralGate is an open LLM compute marketplace with an OpenAI-compatible API. Route requests across local GPU hosters and cloud models — pay per token, earn by hosting.
Quickstart
Make your first API call in under 2 minutes.
Chat API
OpenAI-compatible completions endpoint.
Routing
Control how requests are routed: cheapest, fastest, private.
Become a Hoster
Earn credits by sharing your GPU.
What is NeuralGate?
NeuralGate is a unified API gateway that routes LLM requests to the best available provider — whether that's a local GPU hoster, your own server, or a cloud model. Unlike OpenRouter, NeuralGate allows anyone with a GPU to register as a hoster and earn credits for serving traffic.
- OpenAI-compatible — drop-in replacement for
api.openai.com - Zero prompt logging — your prompts are never stored
- Smart routing — auto-selects best hoster by trust, latency, and price
- Credit economy — earn credits by hosting, spend on other models
- Privacy mode — never fallback to cloud
Base URL
https://api.computeshare.servequake.com/v1Authentication
All API requests require a bearer token in the Authorization header:
Authorization: Bearer ngk_your_api_key_hereGet your API key at /join → create an account → your key is shown once after signup.