Ollama
Open-source tool for running language models locally, complemented by a paid cloud service for developers and teams.
Category: Development & Code · Localization, search & APIs
Features
Ollama is a free open-source tool for local language-model inference on macOS, Windows, and Linux. It supports Llama, Gemma, Mistral, Phi, and dozens of other models via Modelfiles and an OpenAI-compatible REST API.
Costs arise solely from your own hardware and electricity; Ollama itself charges no fees. GPU support covers NVIDIA, AMD, and Apple Silicon. Network peers, keepalive timeouts, and logging are configurable via environment variables.
- Open-source tool to run language models locally such as Llama, Gemma, Mistral, and Phi
- REST API compatible with the OpenAI API for easy integration with existing apps
- Modelfiles to create custom model configurations and system prompts
- GPU support for NVIDIA, AMD, and Apple Silicon for accelerated inference
- Free without usage limits; only hardware and electricity costs apply
- Extensive model library with a daily-growing selection
Prices and plans
| Tier | Price | Period | What you get |
|---|---|---|---|
| Local / Open Source | free | Permanent | per the vendor "open weights and open source", source code on GitHub (github.com/ollama/ollama) runs 100+ models on the user's own hardware, no cloud requirement CLI and local API, integration with coding agents/IDEs |
| Cloud Free | free | Month | cloud model access, 1 concurrent cloud model per the vendor "light cloud usage limits" CLI, API and desktop apps |
| Cloud Pro | 20 $ | Month (200 $/year on annual statement) | Access to larger Pro cloud models and 3 concurrent requests $60 of usage credits per month Fast Mode is still listed as coming soon |
| Cloud Max | 100 $ | Month | $300 of usage credits per month Early access to the newest models 10 concurrent requests |
| Cloud Team | 500 $ | Month (early access) | Unlimited users and $1,000 of shared usage credits per month Centralized billing and administration, priority support Shared projects, skills and instructions are still listed as coming soon |
| Enterprise | contact sales | Custom | volume discounts security support deployment planning |
Similar tools
FAQ
Is Ollama available for free?
Yes. A permanently free plan is published, not a time-limited trial.
Where is Ollama's vendor based?
Ollama, based in USA. For data processing and privacy terms the vendor's own contract governs.
Is Ollama still active?
Active open-source project with an additional paid cloud service (Free/Pro/Max/Team/Enterprise). No duplicate found in the existing catalog (grep over tools.json for "ollama" returned no hits).
How many plans are documented for Ollama?
The catalog documents 6 plans with price, billing period, and included features.
Which use case is Ollama categorized for?
Ollama is listed in the catalog under “Development & Code.”
Where do the details about Ollama come from?
Prices, limits, and product details are documented against the listed official vendor page.
How we compare
We compare free access, paid entry, plan limits, features and the listed official sources. Unsourced figures stay marked as not published.
Only confirmed entries appear in the catalog. Prices, plans and limits come from listed official vendor pages. Missing figures stay marked as not published. Result lists are alphabetical by default and can be switched to Free access first; neither is a quality ranking. The vendor page always wins.
Edited and checked by the AI Compare team
Sources
- https://ollama.com
- https://ollama.com/pricing
Visit site (opens in a new tab)
Spotted an outdated figure? Vendor pages change without notice. Report an error