Ollama
Run open models on local hardware, with larger cloud models available through the same CLI, API, apps, and integrations.
About Ollama
Ollama runs open models on local hardware and carries the same workflow into larger cloud-hosted models when needed. It works through a command-line interface, API, desktop apps, and integrations for coding agents, assistants, and editors. Local execution can remain fully offline, making it useful when data needs to stay on the user’s machine. Cloud access comes with an account and has Free, Pro, and Max tiers; a Team plan is marked as coming soon. Cloud consumption mainly follows GPU time instead of a fixed token allowance, so larger models and longer requests use limits faster. Free covers light cloud work. Pro adds larger models, three concurrent cloud models, and 50 times the Free cloud usage. Max raises concurrency to ten and provides five times the Pro usage. Ollama therefore fits developers who value local control but sometimes need datacenter hardware. Centralized administration, SSO, model controls, and priority support belong to the forthcoming Team offer.
Best for
Best use cases
A developer runs a model locally during routine work, then switches to a larger cloud model for a demanding request.
An agent workflow runs several cloud models in parallel, with concurrency determined by the selected paid plan.
A workstation stays offline for sensitive analysis while the same toolchain remains available through the local CLI and API.
Compare before choosing
Compared with cloud-only model services, Ollama can keep inference on local hardware and operate entirely offline.
Compared with fixed token plans, Ollama cloud usage mainly tracks GPU time, model size, and request duration.
Compared with the Free tier, Pro and Max increase cloud capacity and concurrency, while Team adds administration features when available.
Features
Local model workflows
Run open models on your own hardware for offline or data-sensitive tasks without consuming cloud usage.
Coding and agent automation
Connect Ollama to terminal coding agents and assistants for code editing, research, and continuous agent tasks.
Editor and application integration
Use the CLI and API or connect models to tools such as VS Code Chat and supported personal assistants.
Pros
- Local models can run entirely offline, keeping sensitive work on hardware you control.
- The Free plan costs $0 and local model use remains unlimited across every cloud subscription tier.
- CLI, API, desktop apps, and many community integrations support several development workflows.
Cons
- Cloud plans use session and weekly limits, so sustained workloads can exhaust included capacity.
- The $100 monthly Max plan is a substantial cost for users who only occasionally need cloud acceleration.
- Performance for local models depends on model size, architecture, and the capabilities of your own hardware.
Pricing Plans
Free
- Run models on your own hardware
- Access cloud models with light usage
- Use CLI, API, and desktop apps
- Unlimited public models
- 40,000+ community integrations
Pro
- Everything in Free
- Access larger cloud models
- Run 3 cloud models at a time
- 50x more cloud usage than Free
- Upload and share private models
Max
- Everything in Pro
- Run 10 cloud models at a time
- 5x more usage than Pro
Team
- Shared usage across the team
- Centralized billing and administration
- Single sign-on (SSO)
- Model access controls
- MDM installer for Windows and macOS
- Priority support and a dedicated Slack channel
* Pricing information is for reference only. Please refer to the latest announcement on Ollama's official website.