Deployment Models
Last updated 06/18/2021
Access speech recognition models via APIs without deep data science expertise. Run state-of-the-art Deep Learning models in the cloud or on-premises—wherever your business needs.
Deepgram offers the following deployment models:
| Model | Description |
|---|---|
| Deepgram Hosted | A multi-tenant service running on Deepgram's cloud. |
| On Premise | A dedicated service deployed to customer-requisitioned cloud instances or customer data centers. |
Operational differences
| Operation | Deepgram Hosted (Multi-tenant) | On Premise |
|---|---|---|
| Deployment Location | Deepgram’s infrastructure | Customer-requisitioned cloud instance Customer data center |
| Infrastructure & Backup Responsibility | Deepgram | Customer |
| Updates | Automatic rolling updates | Customer-initiated rolling updates. Excludes critical updates (e.g., security patches), which will be applied as soon as possible. |
| Service & Uptime Reporting | Monitored by Deepgram | Monitored by customer |