Run and configure models
Use open models locally or in the cloud through the CLI and configuration such as Modelfiles.
TOOLORA / Local reading edition
Ollama
Run open models locally or in the cloud and connect them to applications through CLI and APIs.
Overview
Ollama runs and connects open models on macOS, Windows and Linux, with cloud access also available. Users call models from the command line, while developers use APIs for conversation, vision, embeddings or tool calling. Configuration and integration guides support controlling the runtime, connecting desktop tools or building custom AI applications.
- Company country / region
- United States · Published company address
Usage guide & costs
- Billing model
Local and cloud models have different cost models. Cloud usage consumes token-based credits, included in plans or purchased separately.
Official details ↗- Before you start
Running models on your own hardware does not consume Ollama cloud credits. Provide suitable hardware and check each model’s license.
Official details ↗
Capabilities
Apps and agent integrations
Connect apps and coding agents through API capabilities including streaming, vision, embeddings, structured output and tool calling.
Official sources and references
- Official websitehttps://ollama.com/
- Documentationhttps://docs.ollama.com/
- Pricing sourcehttps://ollama.com/pricing
Descriptions summarize public information; consult official websites for features, pricing and regional availability.