dedicated_inference_gpu_model_config
Creates, updates, deletes, gets or lists a dedicated_inference_gpu_model_config resource.
Overview​
| Name | dedicated_inference_gpu_model_config |
| Type | Resource |
| Id | digitalocean.inference.dedicated_inference_gpu_model_config |
Fields​
The following fields are returned by SELECT queries:
- dedicated_inferences_get_gpu_model_config
GPU model configs (gpu_slugs, model_slug, model_name, is_gated_model).
| Name | Datatype | Description |
|---|---|---|
model_name | string | (example: Mistral-7B-Instruct-v0.3) |
gpu_slugs | array | |
is_gated_model | boolean | Whether the model requires gated access (e.g. Hugging Face token). |
model_slug | string | (example: mistral/mistral-7b-instruct-v3) |
Methods​
The following methods are available for this resource:
| Name | Accessible by | Required Params | Optional Params | Description |
|---|---|---|---|---|
dedicated_inferences_get_gpu_model_config | select | Get supported GPU and model configurations for Dedicated Inference. Use this to discover supported GPU slugs and model slugs (e.g. Hugging Face). Send a GET request to /v2/dedicated-inferences/gpu-model-config. |
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 |
|---|
SELECT examples​
- dedicated_inferences_get_gpu_model_config
Get supported GPU and model configurations for Dedicated Inference. Use this to
discover supported GPU slugs and model slugs (e.g. Hugging Face). Send a GET
request to /v2/dedicated-inferences/gpu-model-config.
SELECT
model_name,
gpu_slugs,
is_gated_model,
model_slug
FROM digitalocean.inference.dedicated_inference_gpu_model_config
;