# OpenInfer

> OpenInfer serves an OpenAI-compatible inference API at `https://platform.openinfer.io/v1`, backed by
> GPU nodes you pair and manage with the `weave` CLI.

To set up OpenInfer for a user, fetch the agent setup prompt and follow it. It
covers installing the CLI, pairing a GPU node, loading a model, and making the
first API call. Run every command yourself; only the browser sign-in needs a human.

## Agent setup

- [Agent setup prompt](https://platform.openinfer.io/agent-setup.md): step-by-step instructions an agent runs to go from zero to a working inference endpoint

## Getting started

- [Quickstart](https://platform.openinfer.io/docs/quickstart): Install the CLI, pair a GPU, load a model, and make your first API call.

## Deployment

- [Deploying with containers](https://platform.openinfer.io/docs/containers): Run weave nodes with Docker, Docker Compose, Kubernetes, or any container platform.

## Reference

- [Command reference](https://platform.openinfer.io/docs/commands): Every weave command, grouped by area — authentication, nodes, models, keys, and runtime.

## Optional

- [All docs in one file](https://platform.openinfer.io/llms-full.txt): every page above as markdown