> For the complete documentation index, see [llms.txt](https://docs.eyepop.ai/developer-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.eyepop.ai/developer-documentation/deploying/cloud.md).

# Cloud

Run Pops on EyePop-hosted infrastructure

Run your Pops on infrastructure hosted and managed by EyePop — no servers to provision. Every cloud workload uses one of two session types.

### Choose a session type

|                       | [Development](/developer-documentation/deploying/cloud/development.md) | [Deployment](/developer-documentation/deploying/cloud/deployment.md) |
| --------------------- | ---------------------------------------------------------------------- | -------------------------------------------------------------------- |
| Session               | transient                                                              | persistent                                                           |
| Created by            | SDK, on demand                                                         | CLI or dashboard, ahead of time                                      |
| Lifetime              | idles out when unused                                                  | stays running, no idle expiry                                        |
| Models                | load on first use (cold start)                                         | pre-loaded (no cold start)                                           |
| Pop binding           | passed by the client at connect                                        | set when the Deployment is created                                   |
| Session UUID required | no                                                                     | yes                                                                  |
| Best for              | building, testing, batch                                               | production, real-time, 24/7                                          |

Start in Development, and promote to a Deployment when you need production latency.

### Next steps

* [Development](/developer-documentation/deploying/cloud/development.md) — connect the SDK and run your first cloud inference
* [Deployment](/developer-documentation/deploying/cloud/deployment.md) — create a persistent session and attach to it
* [Private cameras](/developer-documentation/deploying/cloud/private-cameras.md) — cloud inference for cameras behind a firewall
* [On-Premise](/developer-documentation/deploying/on-premise.md) — run the runtime inside your own infrastructure instead