Ollama

Ollama is a platform for running and building with open AI models, either locally on macOS, Windows and Linux or in the cloud. It lets developers pull and run open models on their own machines, and call larger cloud hosted models through the same interface. The company states that prompts are never stored or trained on. It is used by developers, researchers and teams who want privacy, control over their model stack, or an easy way to try the latest open models without managing infrastructure. Cloud usage is billed through usage credits, with a published per million token price list for models such as the DeepSeek, GLM, Kimi, MiniMax, Mistral, Nemotron, Gemma and gpt oss families, and lower off peak pricing on some models outside 12:00 to 18:00 UTC on weekdays and all day on weekends. Plans on the pricing page are Free at $0, which includes running models locally, starter usage credits and starter model access, with no service fees and credits that can be added to unlock all models. Pro is $20 a month, or $200 a year billed annually, and includes $60 of monthly usage credits, larger pro models and concurrent models. Max is $100 a month with $300 of monthly credits, early model access and 10 concurrent requests. Team is $500 a month with unlimited users and $1,000 of shared monthly credits. Enterprise is custom priced and adds model access controls, cost budgets and dedicated support.