Ollama Cloud
Hosted inference for the same open models, called from the Ollama CLI or an application with an API key and served from the US, Europe and Singapore.
Find alternatives to Ollama Cloud
Five plans on ollama.com/pricing: Free $0 with starter usage credits, Pro $20/mo or $200/yr with $60 of monthly usage credit, Max $100/mo with $300, Team $500/mo with $1,000 shared, and Enterprise on custom volume pricing. Cloud usage is drawn against credits; local inference stays free.
What it does
- Model inference
- Model hosting
Sources
- Pricing
-
All five plan names, prices and credit allowances quoted from the page, 2026-09-18.
- Description
-
Official documentation · 18 Sep 2026
The docs' own first line: 'Run models in Ollama's cloud from your apps or terminal. No model or app download required.'
- Sold within
-
Subscribed to directly; the plans buy cloud usage, not an add-on to something else.
- URL
-
Official documentation · 18 Sep 2026
Fetched 2026-09-18, 200. Cloud has no marketing page of its own; the docs page plus the priced plans on ollama.com/pricing are the record's evidence.
- Interfaces
-
Official documentation · 29 Sep 2026
Docs give a curl example against https://ollama.com/api/chat ('Send a request from the same terminal'), state OpenAI/Anthropic-compatible clients can also be used, and give 'ollama' as the terminal command after installing the app.
Also from Ollama
-
Ollama Infrastructure service
MIT-licensed local model runner for macOS, Windows and Linux that downloads open models and serves them from one command, with an OpenAI-compatible API on the machine it runs on.
Something wrong here? Send a correction — quote this product id: ollama-cloud.