- Starting price
- $20/mo. or $200/yr billed annually
- Pricing
- Free plan
- Website
- ollama.com
About Ollama
Ollama lets you run open models locally or in the cloud, enabling coding agents to operate with private data and lower costs. It’s built for developers and teams building AI-assisted workflows who want model access without sacrificing data control.
Key Features
To help teams balance speed, privacy, and model choice, Ollama provides a local-first runtime with flexible model access and cloud options:
Dedicated throughput
Throughput stays steady under multi-agent workloads thanks to dedicated capacity; benchmarks show Ollama around 195.6 tokens/sec, versus peers ~97.6–63 tokens/sec.
Frontier open models
Access recent open models with favorable cost-per-performance, including gpt-5.6-sol[max] at about 73% ±3% for $6.46 and claude-fable-5[max] at 70% ±4% for $21.63.
One-command model launches
Start Claude Code, Codex, OpenCode, Hermes Agent, and more with a single command; you can switch models without changing your workflow.
Privacy and hosting controls
Your prompts aren’t trained on; cloud models hosted in the US, Europe, and Singapore, while local runs stay on your machine and weights are open where applicable.
Summary
Best for AI-powered developer teams, data-sensitive workflows, and ops teams building AI copilots.
Pricing
View pricingPlans and prices as listed on ollama.com as of Sep 22, 2026.
Free
$0 / monthly
- Run models locally
- Starter usage credits included
- Includes access to starter models
- Add credits to unlock all models
- No service fees
Pro
$20 / mo. or $200/yr billed annually / monthly/annual
- For shorter, well-defined day-to-day tasks
- $60 of usage credits per month
- Access to larger pro models
- Run multiple models concurrently
- Fast mode (coming soon)
Max
$100 / mo. / monthly
- For power users who run multiple agents simultaneously
- Everything in Free and Pro, plus
- $300 of usage credits per month
- Early access to the newest models
- 10 concurrent requests
Team
$500 / mo. / monthly
- For teams scaling with open models
- Unlimited users
- $1,000 of usage credits per month, shared across the team
- Centralized billing and administration
- Priority support
- Shared projects, skills, and instructions (coming soon)
Enterprise
Custom / custom
- For larger teams with volume usage pricing
- Everything in Team, plus
- Model access controls
- Set cost budgets for users and API keys
- Private Slack channel with dedicated support
- Custom security questionnaires
