dedicated_inferences

Creates, updates, deletes, gets or lists a dedicated_inferences resource.

Overview

Name	dedicated_inferences
Type	Resource
Id	digitalocean.inference.dedicated_inferences

Fields

The following fields are returned by SELECT queries:

dedicated_inferences_get

Response containing a single Dedicated Inference instance.

Name	Datatype	Description
id	string (uuid)	Unique ID of the Dedicated Inference. (example: 6b5c619c-359c-44ca-87e2-47e98170c01d)
created_at	string (date-time)	When the Dedicated Inference was created. (example: 2024-01-09T20:44:32Z)
endpoints	object
pending_deployment_spec	object	Pending deployment when status is provisioning or updating.
region	string	DigitalOcean region where the Dedicated Inference is hosted. (example: atl1)
spec	object	Structured configuration for a Dedicated Inference deployment.
status	string	Current state of the Dedicated Inference. (active, new, provisioning, updating, deleting, error) (example: active)
updated_at	string (date-time)	When the Dedicated Inference was last updated. (example: 2024-01-09T20:44:32Z)
vpc_uuid	string (uuid)	VPC UUID of the Dedicated Inference. (example: 997615ce-132d-4bae-9270-9ee21b395e5d)

dedicated_inferences_list

The response will be a JSON object with a key called dedicated_inferences. This will be set to an array of objects, each of which will contain the standard attributes associated with a Dedicated Inference. Pagination uses the same links and meta structure as other list endpoints.

Name	Datatype	Description
id	string (uuid)	Unique ID of the Dedicated Inference. (example: 6b5c619c-359c-44ca-87e2-47e98170c01d)
created_at	string (date-time)	When the Dedicated Inference was created. (example: 2024-01-09T20:44:32Z)
endpoints	object
pending_deployment_spec	object	Pending deployment when status is provisioning or updating.
region	string	DigitalOcean region where the Dedicated Inference is hosted. (example: atl1)
spec	object	Structured configuration for a Dedicated Inference deployment.
status	string	Current state of the Dedicated Inference. (active, new, provisioning, updating, deleting, error) (example: active)
updated_at	string (date-time)	When the Dedicated Inference was last updated. (example: 2024-01-09T20:44:32Z)
vpc_uuid	string (uuid)	VPC UUID of the Dedicated Inference. (example: 997615ce-132d-4bae-9270-9ee21b395e5d)

Methods

The following methods are available for this resource:

Name	Accessible by	Required Params	Optional Params	Description
dedicated_inferences_get	select	dedicated_inference_id		Retrieve an existing Dedicated Inference by ID. Send a GET request to /v2/dedicated-inferences/{dedicated_inference_id}. The status in the response is one of active, new, provisioning, updating, deleting, or error.
dedicated_inferences_list	select		per_page, page, region	List all Dedicated Inference instances for your team. Send a GET request to /v2/dedicated-inferences. You may filter by region and use page and per_page for pagination.
dedicated_inferences_create	insert	spec		Create a new Dedicated Inference for your team. Send a POST request to /v2/dedicated-inferences with a spec object (version, name, region, vpc, enable_public_endpoint, model_deployments) and optional access_tokens (e.g. hugging_face_token for gated models). The response code 202 Accepted indicates the request was accepted for processing; it does not indicate success or failure. The token value is returned only on create; store it securely.
dedicated_inferences_patch	update	dedicated_inference_id		Update an existing Dedicated Inference. Send a PATCH request to /v2/dedicated-inferences/{dedicated_inference_id} with updated spec and/or access_tokens. Status will move to updating and return to active when done.
dedicated_inferences_delete	delete	dedicated_inference_id		Delete an existing Dedicated Inference. Send a DELETE request to /v2/dedicated-inferences/{dedicated_inference_id}. The response 202 Accepted indicates the request was accepted for processing.

Parameters

Parameters can be passed in the WHERE clause of a query. Check the Methods section to see which parameters are required or optional for each operation.

Name	Datatype	Description
dedicated_inference_id	string (uuid)	A unique identifier for a Dedicated Inference instance. (example: 6b5c619c-359c-44ca-87e2-47e98170c01d)
page	integer	Which 'page' of paginated results to return. (example: 1)
per_page	integer	Number of items returned per page (example: 2)
region	string	Filter by region. Dedicated Inference is only available in nyc2, tor1, and atl1. (example: atl1)

SELECT examples

dedicated_inferences_get

Retrieve an existing Dedicated Inference by ID. Send a GET request to
/v2/dedicated-inferences/{dedicated_inference_id}. The status in the response
is one of active, new, provisioning, updating, deleting, or error.

SELECT
id,
created_at,
endpoints,
pending_deployment_spec,
region,
spec,
status,
updated_at,
vpc_uuid
FROM digitalocean.inference.dedicated_inferences
WHERE dedicated_inference_id = '{{ dedicated_inference_id }}' -- required
;

dedicated_inferences_list

List all Dedicated Inference instances for your team. Send a GET request to
/v2/dedicated-inferences. You may filter by region and use page and per_page
for pagination.

SELECT
id,
created_at,
endpoints,
pending_deployment_spec,
region,
spec,
status,
updated_at,
vpc_uuid
FROM digitalocean.inference.dedicated_inferences
WHERE per_page = '{{ per_page }}'
AND page = '{{ page }}'
AND region = '{{ region }}'
;

INSERT examples

dedicated_inferences_create

Create a new Dedicated Inference for your team. Send a POST request to
/v2/dedicated-inferences with a spec object (version, name, region, vpc,
enable_public_endpoint, model_deployments) and optional access_tokens (e.g.
hugging_face_token for gated models). The response code 202 Accepted indicates
the request was accepted for processing; it does not indicate success or failure.
The token value is returned only on create; store it securely.

INSERT INTO digitalocean.inference.dedicated_inferences (
spec,
access_tokens
)
SELECT 
'{{ spec }}' /* required */,
'{{ access_tokens }}'
RETURNING
dedicated_inference,
token
;

Manifest

# Description fields are for documentation purposes
- name: dedicated_inferences
props:
  - name: spec
    description: |
      Structured configuration for a Dedicated Inference deployment.
    value:
      version: {{ version }}
      name: "{{ name }}"
      region: "{{ region }}"
      vpc:
        uuid: "{{ uuid }}"
      enable_public_endpoint: {{ enable_public_endpoint }}
      model_deployments:
        - model_id: "{{ model_id }}"
          model_slug: "{{ model_slug }}"
          model_provider: "{{ model_provider }}"
          workload_config: "{{ workload_config }}"
          accelerators: "{{ accelerators }}"
  - name: access_tokens
    value: "{{ access_tokens }}"
    description: |
      Key-value pairs for provider tokens (e.g. Hugging Face).

UPDATE examples

dedicated_inferences_patch

Update an existing Dedicated Inference. Send a PATCH request to
/v2/dedicated-inferences/{dedicated_inference_id} with updated spec and/or
access_tokens. Status will move to updating and return to active when done.

UPDATE digitalocean.inference.dedicated_inferences
SET 
spec = '{{ spec }}',
access_tokens = '{{ access_tokens }}'
WHERE 
dedicated_inference_id = '{{ dedicated_inference_id }}' --required
RETURNING
dedicated_inference;

DELETE examples

dedicated_inferences_delete

Delete an existing Dedicated Inference. Send a DELETE request to
/v2/dedicated-inferences/{dedicated_inference_id}. The response 202 Accepted
indicates the request was accepted for processing.

DELETE FROM digitalocean.inference.dedicated_inferences
WHERE dedicated_inference_id = '{{ dedicated_inference_id }}' --required
;