TextSynth is an AI tool providing API access and a playground for large language, text-to-image, text-to-speech, and speech-to-text models like Mistral and Stable Diffusion.

Ollama

Free

Web

model serving

Ollama is a platform for running large language models locally on macOS, Linux, and Windows, enabling easy access to models such as Llama 3.3 and Gemma 3.

Inferenceable

Free

Web

model serving

Inferenceable is an open-source, super simple, pluggable, and production-ready AI inference server written in Node.js, utilizing llama.cpp and llamafile.