Open source & self-hosted · Powered by llms.py

Self-host 530+ AI models
for text, image & audio

A lightweight, OpenAI-compatible CLI & server gateway — the open Open WebUI alternative. Generate anything across 24 providers, then publish it to the public gallery.

Explore the Gallery Get llms.py

llms --serve 8000

530+

Models

24

Providers

3

Modalities · Text · Image · Audio

100%

Open source & self-hosted

OpenAIAnthropicGoogle GeminiGroqMistralOpenRouterxAI GrokDeepSeekQwenZ.aiChutesNvidiaOllamaTogether

One tool, every modality

Generate anything

From a single self-hosted gateway — chat, create images, and synthesize speech through one clean, OpenAI-compatible API and UI.

Text & Chat

A fast, private, ChatGPT-like web UI over every local & cloud LLM — with tools, MCP, skills, agents and 200+ system prompts.

$ llms "Explain quantum tunneling"

Image Generation

Create images via Gemini, OpenAI, OpenRouter, Chutes, Z.ai & Nvidia — right inside the gallery workflow.

Audio & Speech

High-quality text-to-speech with Gemini 2.5 Flash/Pro — plus voice-to-text input via the microphone.

Create → Publish → Showcase

Your creations, in a public gallery

Anything you generate in llms.py can be published with one click — and it lands in the live media gallery hosted right here, browsable by everyone with categories, tags, ratings and infinite scroll.