This repository contains the documentation website for Inference Gateway, an open-source API gateway for Large Language Models (LLMs) that provides a unified interface for accessing multiple AI providers.

Inference Gateway offers a unified API layer to interact with multiple LLM providers including OpenAI, DeepSeek, Anthropic, Groq, Cohere, Ollama and more. It provides a consistent interface for interacting with different LLMs, abstracting away the differences between each provider's API.

This documentation site is built with VitePress 1.x and Vue 3.

# Install dependencies
npm install

# Start development server
npm run dev

# Static build → .vitepress/dist/
npm run build

# Markdown linting
npm run lint:md

# Prettier formatting
npm run format
npm run format:check

You can use flox for a consistent development environment (configured in .flox/env/manifest.toml).

See AGENTS.md or CLAUDE.md for the full list of commands and development conventions.

Contributions to improve the documentation are welcome! You can:

1. Edit existing Markdown files at the repo root (each *.md file becomes a page)
2. Add new documentation pages by creating *.md files at the repo root
3. Improve the site's design and functionality

This site migrated from Next.js/MDX to VitePress. Content is authored as plain Markdown (.md) files — no markdown/ directory or MDX extension is used.

This project is licensed under the Apache 2.0 License.