Ollama

Worried about costs? No Problem! With Ollama you can run LLMs like LLaMA and Mistral on your own machine for free. Ideal for offline development, edge applications, and private inference without relying on cloud services.

Supported	All Ollama APIs (2025.04.23)
	💬 Chat Completion, Stream, Completion
	🧠 Embeddings
	🛠️ Models, Model Management
	🛠️ Version