| Cloud Inference Approaches |
Pick the Model that Fits Your Budget and Speed Needs |
<strong>Inference speeds vary by model size and type.</strong> You're billed per token on the text or images you embed, and the rate depends on the model: several are free, others are metered. Inference speed varies by model too, so a cheaper model isn't always the faster one. You can read more about <a href="/documentation/search-patterns/choose-embedding-model/">choosing an embedding model</a>, or contact us to talk through sizing. |
| text |
url |
| Talk Through Sizing With Our Team |
/contact-us/ |
|
| id |
featureCellWidth |
cols |
features |
| cloud-inference-approaches |
17rem |
| id |
name |
highlight |
bold |
icon |
| managedCloud |
Managed Cloud |
false |
false |
| src |
alt |
| /icons/outline/cloud-managed-violet.svg |
Managed cloud |
|
|
| id |
name |
highlight |
bold |
icon |
| hybridCloud |
Hybrid Cloud |
false |
false |
| src |
alt |
| /icons/outline/cloud-hybrid-blue.svg |
Hybrid cloud |
|
|
| id |
name |
highlight |
bold |
icon |
| privateCloudOss |
Private Cloud/OSS |
false |
false |
| src |
alt |
| /icons/outline/cloud-private-teal.svg |
Private cloud |
|
|
|
| name |
managedCloud |
hybridCloud |
privateCloudOss |
| Qdrant-hosted embedding models |
Available: automatically enabled on new clusters |
Not available |
Not available |
|
| name |
managedCloud |
hybridCloud |
privateCloudOss |
| In-cluster proxy to externally hosted models |
Available |
Not available |
Not available |
|
| name |
managedCloud |
hybridCloud |
privateCloudOss |
| In-cluster BM25 |
Available |
Available |
Available |
|
|
|
|
true |
