Ollama

Ollama is an AI model runtime and developer platform designed for developers, AI engineers, researchers, privacy-focused users, and organizations that want to run open models locally or access larger models through the cloud. It is available for macOS, Windows, and Linux and provides a command-line interface and desktop experience for downloading, managing, and interacting with models. Local models can run entirely on the user's hardware without sending prompts or responses to Ollama.

Users can choose models from Ollama's model library and run them for chat, reasoning, coding, document analysis, vision, embeddings, and agent workflows depending on the capabilities of each model. Ollama supports features including streaming, structured outputs, thinking models, vision inputs, embeddings, tool calling, and web search. Developers can create applications through Ollama's REST API and official Python and JavaScript libraries. The API can operate locally or connect to Ollama Cloud using a similar interface.

Ollama also provides compatibility with parts of the OpenAI API and Anthropic-compatible workflows. Integrations are available for development and automation tools including Claude Code, OpenCode, Codex, VS Code, JetBrains, Cline, n8n, and other AI applications. This makes Ollama useful as a local model backend for coding agents, RAG systems, automation workflows, and custom AI applications.

Ollama offers a $0 Free plan with unlimited public models running on personal hardware and limited cloud usage. Pro costs $20 per month or $200 annually and provides 50 times more cloud usage plus three concurrent cloud models. Max costs $100 per month but new subscriptions are currently paused. Team pricing is $25 per seat per month with a five-seat minimum and is currently waitlisted. Enterprise pricing is custom. Local model usage remains unlimited regardless of plan while cloud plans have session and weekly usage limits.