> ## Documentation Index
> Fetch the complete documentation index at: https://runpod-b18f5ded-promptless-websocket-streaming-tutorial.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Manage Endpoints

`gpuIds`, `name`, and `templateId` are required arguments; all other arguments are optional, and default values will be used if unspecified.

## Create a new Serverless Endpoint

<Tabs>
  <Tab title="cURL">
    ```bash theme={null}
    curl --request POST \
      --header 'content-type: application/json' \
      --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
      --data '{"query": "mutation { saveEndpoint(input: { gpuIds: \"AMPERE_16\", idleTimeout: 5, locations: \"US\", name: \"Generated Endpoint -fb\", networkVolumeId: \"\", scalerType: \"QUEUE_DELAY\", scalerValue: 4, templateId: \"xkhgg72fuo\", workersMax: 3, workersMin: 0 }) { gpuIds id idleTimeout locations name scalerType scalerValue templateId workersMax workersMin } }"}'
    ```
  </Tab>

  <Tab title="GraphQL">
    ```GraphQL theme={null}
    mutation {
      saveEndpoint(input: {
        # options for gpuIds are "AMPERE_16,AMPERE_24,ADA_24,AMPERE_48,ADA_48_PRO,AMPERE_80,ADA_80_PRO"
        gpuIds: "AMPERE_16",
        idleTimeout: 5,
        # leave locations as an empty string or null for any region
        # options for locations are "CZ,FR,GB,NO,RO,US"
        locations: "US",
        # append -fb to your endpoint's name to enable FlashBoot
        name: "Generated Endpoint -fb",
        # uncomment below and provide an ID to mount a network volume to your workers
        # networkVolumeId: "",
        scalerType: "QUEUE_DELAY",
        scalerValue: 4,
        templateId: "xkhgg72fuo",
        workersMax: 3,
        workersMin: 0
      }) {
        gpuIds
        id
        idleTimeout
        locations
        name
        # networkVolumeId
        scalerType
        scalerValue
        templateId
        workersMax
        workersMin
      }
    }
    ```
  </Tab>

  <Tab title="Output">
    ```json theme={null}
    {
      "data": {
        "saveEndpoint": {
          "gpuIds": "AMPERE_16",
          "id": "i02xupws21hp6i",
          "idleTimeout": 5,
          "locations": "US",
          "name": "Generated Endpoint -fb",
          "scalerType": "QUEUE_DELAY",
          "scalerValue": 4,
          "templateId": "xkhgg72fuo",
          "workersMax": 3,
          "workersMin": 0
        }
      }
    }
    ```
  </Tab>
</Tabs>

## Modify an existing Serverless Endpoint

<Tabs>
  <Tab title="cURL">
    ```bash theme={null}
    curl --request POST \
      --header 'content-type: application/json' \
      --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
      --data '{"query": "mutation { saveEndpoint(input: { id: \"i02xupws21hp6i\", gpuIds: \"AMPERE_16\", name: \"Generated Endpoint -fb\", templateId: \"xkhgg72fuo\", workersMax: 0 }) { id gpuIds name templateId workersMax } }"}'
    ```
  </Tab>

  <Tab title="GraphQL">
    ```GraphQL theme={null}
    mutation {
      saveEndpoint(input: {
        id: "i02xupws21hp6i",
        gpuIds: "AMPERE_16",
        name: "Generated Endpoint -fb",
        templateId: "xkhgg72fuo",
        # Modify your template options here (or above, if applicable).
        # For this example, we've modified the endpoint's max workers.
        workersMax: 0
      }) {
        id
        gpuIds
        name
        templateId
        # You can include what you've changed here, too.
        workersMax
      }
    }
    ```
  </Tab>

  <Tab title="Output">
    ```json theme={null}
    {
      "data": {
        "saveEndpoint": {
          "id": "i02xupws21hp6i",
          "gpuIds": "AMPERE_16",
          "name": "Generated Endpoint -fb",
          "templateId": "xkhgg72fuo",
          "workersMax": 0
        }
      }
    }
    ```
  </Tab>
</Tabs>

## View your Endpoints

<Tabs>
  <Tab title="cURL">
    ```bash theme={null}
    curl --request POST \
         --header 'content-type: application/json' \
         --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
         --data '{"query": "query Endpoints { myself { endpoints { gpuIds id idleTimeout locations name networkVolumeId pods { desiredStatus } scalerType scalerValue templateId workersMax workersMin } serverlessDiscount { discountFactor type expirationDate } } }"}'
    ```
  </Tab>

  <Tab title="GraphQL">
    ```GraphQL theme={null}
    query Endpoints {
      myself {
        endpoints {
          gpuIds
          id
          idleTimeout
          locations
          name
          networkVolumeId
          pods {
            desiredStatus
          }
          scalerType
          scalerValue
          templateId
          workersMax
          workersMin
        }
        serverlessDiscount {
          discountFactor
          type
          expirationDate
        }
      }
    }
    ```
  </Tab>

  <Tab title="Output">
    ```json theme={null}
    {
      "data": {
        "myself": {
          "endpoints": [
            {
              "gpuIds": "AMPERE_16",
              "id": "i02xupws21hp6i",
              "idleTimeout": 5,
              "locations": "US",
              "name": "Generated Endpoint -fb",
              "networkVolumeId": null,
              "pods": [],
              "scalerType": "QUEUE_DELAY",
              "scalerValue": 4,
              "templateId": "xkhgg72fuo",
              "workersMax": 0,
              "workersMin": 0
            }
          ],
          "serverlessDiscount": null
        }
      }
    }
    ```
  </Tab>
</Tabs>

## Delete a Serverless Endpoints

Note that your endpoint's min and max workers must both be set to zero for your call to work.

<Tabs>
  <Tab title="cURL">
    ```bash theme={null}
    curl --request POST \
    	--header 'content-type: application/json' \
      --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
      --data '{"query": "mutation { deleteEndpoint(id: \"i02xupws21hp6i\") }"}'
    ```
  </Tab>

  <Tab title="GraphQL">
    ```GraphQL theme={null}
    mutation {
      deleteEndpoint(id: "i02xupws21hp6i")
    }
    ```
  </Tab>

  <Tab title="Output">
    ```json theme={null}
    {
      "data": {
        "deleteEndpoint": null
      }
    }
    ```
  </Tab>
</Tabs>