[ Web Proxy ]
URL:
Viewing: https://docs.digitalocean.com/reference/terraform/reference/resources/dedicated_inference/ [Back]  [Original]
digitalocean_dedicated_inference | DigitalOcean Documentation

For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

digitalocean_dedicated_inference

Generated on 18 Aug 2026 from Terraform version v2.100.0

Copy page as Markdown View page as Markdown

Provides a DigitalOcean Dedicated Inference resource. This can be used to create, modify, and delete dedicated inference endpoints for running GPU-accelerated model inference.

Example Usage 

resource "digitalocean_dedicated_inference" "example" {
  name   = "my-inference-endpoint"
  region = "tor1"

  model_deployments {
    model_slug     = "deepseek-r1-distill-qwen-14b"
    model_provider = "digitalocean"

    accelerators {
      accelerator_slug = "gpu-h100x1-80gb"
      scale            = 1
      type             = "nvidia_h100"
    }
  }
}

With Public Endpoint 

resource "digitalocean_dedicated_inference" "public" {
  name                   = "my-public-inference"
  region                 = "tor1"
  enable_public_endpoint = true

  model_deployments {
    model_slug     = "deepseek-r1-distill-qwen-14b"
    model_provider = "digitalocean"

    accelerators {
      accelerator_slug = "gpu-h100x1-80gb"
      scale            = 1
      type             = "nvidia_h100"
    }
  }
}

With VPC 

resource "digitalocean_dedicated_inference" "private" {
  name     = "my-private-inference"
  region   = "tor1"
  vpc_uuid = digitalocean_vpc.example.id

  model_deployments {
    model_slug     = "deepseek-r1-distill-qwen-14b"
    model_provider = "digitalocean"

    accelerators {
      accelerator_slug = "gpu-h100x1-80gb"
      scale            = 1
      type             = "nvidia_h100"
    }
  }
}

Argument Reference

The following arguments are supported:

Attributes Reference

In addition to the arguments listed above, the following attributes are exported:

Import

Dedicated inference endpoints can be imported using their id, e.g.

terraform import digitalocean_dedicated_inference.example endpoint-id

Timeouts

digitalocean_dedicated_inference provides the following Timeouts configuration options:

In this article...

We can't find any results for your search.

Try using different keywords or simplifying your search terms.

Web Proxy Viewer  |  New URL  |  Original Page