Files
ollama/docs/cloud.mdx

43 lines
1.8 KiB
Plaintext

---
title: Cloud
sidebarTitle: Overview
---
Run larger models in Ollama's cloud without requiring a powerful GPU. Inference runs on Ollama's cloud service.
[System One](/capabilities/decision#use-a-cloud-model) is also available in the cloud for classification, yes/no questions, and scoring. Supported capabilities vary by model. Cloud models currently do not support [structured outputs](/capabilities/structured-outputs).
## Choose how to connect
<CardGroup cols={2}>
<Card title="Creating an API key" icon="key" href="/cloud/api">
Call `https://ollama.com/api` directly without installing Ollama.
</Card>
<Card title="Models" icon="cloud" href="/cloud/models">
Run cloud models from the Ollama app, CLI, local API, or official libraries.
</Card>
<Card title="Usage" icon="chart-line" href="/cloud/usage">
Review usage, balances, plans, and API reporting.
</Card>
<Card title="FAQ" icon="circle-question" href="/cloud/faq">
Find answers about accounts, authentication, privacy, and requests.
</Card>
</CardGroup>
Both connection methods require an Ollama account. Browse the available models in the [cloud model library](https://ollama.com/search?c=cloud).
## Use only local models
To keep inference on your own hardware, follow [Run a model locally](/quickstart#run-a-model-locally). You can also [disable cloud features](/faq#how-do-i-disable-ollama-cloud-features).
## Retirements
Cloud models may be deprecated as newer models become available. See [Cloud model lifecycle](/cloud/model-lifecycle) for upcoming and past retirements.
## Data handling
Ollama processes cloud prompts and responses to answer your requests. We do not use them to train models. Read the [Privacy Policy](https://ollama.com/privacy) for details or see the [Cloud FAQ](/cloud/faq).