LocalAI

What is LocalAI?

LocalAI is a free, open-source alternative to the OpenAI API. It is a drop-in replacement that runs locally on CPU or GPU with no API keys required. It supports multiple model formats and is compatible with OpenAI's full API spec.

What It Replaces

• POST /v1/chat/completions — LLM chat (GPT-4 equivalent)
• POST /v1/completions — text completion
• POST /v1/embeddings — generate embeddings
• POST /v1/images/generations — image generation (Stable Diffusion)
• POST /v1/audio/transcriptions — speech to text (Whisper)
• POST /v1/audio/speech — text to speech

Quick Start

docker run -p 8080:8080 localai/localai:latest-aio-cpu

Then call:

curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello"}]}'

When to Use LocalAI vs. Ollama

• Ollama — best for running individual LLM models locally with a clean CLI.
• LocalAI — best when you need to self-host the full OpenAI API surface (including embeddings, image gen, TTS) and want your existing OpenAI-built apps to work without code changes.