Manage Pods

Create, start, stop, and query Pods using the GraphQL API with cURL and GraphQL examples. For the complete schema, see the GraphQL Spec.

Quick reference

Operation	Mutation/Query
Create on-demand Pod	`podFindAndDeployOnDemand`
Create spot Pod	`podRentInterruptable`
Start Pod	`podResume`
Start spot Pod	`podBidResume`
Stop Pod	`podStop`
List all Pods	`myself { pods { ... } }`
Get Pod by ID	`pod(input: {podId: "..."})`
List GPU types	`gpuTypes`

Create a Pod

On-demand Pod

On-demand Pods provide guaranteed compute at a fixed price.

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "mutation { podFindAndDeployOnDemand( input: { cloudType: ALL, gpuCount: 1, volumeInGb: 40, containerDiskInGb: 40, minVcpuCount: 2, minMemoryInGb: 15, gpuTypeId: \"NVIDIA RTX A6000\", name: \"Runpod Tensorflow\", imageName: \"runpod/tensorflow\", dockerArgs: \"\", ports: \"8888/http\", volumeMountPath: \"/workspace\", env: [{ key: \"JUPYTER_PASSWORD\", value: \"your-password\" }] } ) { id imageName env machineId machine { podHostId } } }"}'

mutation {
  podFindAndDeployOnDemand(
    input: {
      cloudType: ALL
      gpuCount: 1
      volumeInGb: 40
      containerDiskInGb: 40
      minVcpuCount: 2
      minMemoryInGb: 15
      gpuTypeId: "NVIDIA RTX A6000"
      name: "Runpod Tensorflow"
      imageName: "runpod/tensorflow"
      dockerArgs: ""
      ports: "8888/http"
      volumeMountPath: "/workspace"
      env: [{ key: "JUPYTER_PASSWORD", value: "your-password" }]
    }
  ) {
    id
    imageName
    env
    machineId
    machine {
      podHostId
    }
  }
}

{
  "data": {
    "podFindAndDeployOnDemand": {
      "id": "50qynxzilsxoey",
      "imageName": "runpod/tensorflow",
      "env": ["JUPYTER_PASSWORD=your-password"],
      "machineId": "hpvdausak8xb",
      "machine": {
        "podHostId": "50qynxzilsxoey-64410065"
      }
    }
  }
}

Spot Pod

Spot Pods offer lower prices but can be interrupted when demand is high.

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "mutation { podRentInterruptable( input: { bidPerGpu: 0.2, cloudType: SECURE, gpuCount: 1, volumeInGb: 40, containerDiskInGb: 40, minVcpuCount: 2, minMemoryInGb: 15, gpuTypeId: \"NVIDIA RTX A6000\", name: \"Runpod Pytorch\", imageName: \"runpod/pytorch\", dockerArgs: \"\", ports: \"8888/http\", volumeMountPath: \"/workspace\", env: [{ key: \"JUPYTER_PASSWORD\", value: \"your-password\" }] } ) { id imageName env machineId machine { podHostId } } }"}'

mutation {
  podRentInterruptable(
    input: {
      bidPerGpu: 0.2
      cloudType: SECURE
      gpuCount: 1
      volumeInGb: 40
      containerDiskInGb: 40
      minVcpuCount: 2
      minMemoryInGb: 15
      gpuTypeId: "NVIDIA RTX A6000"
      name: "Runpod Pytorch"
      imageName: "runpod/pytorch"
      dockerArgs: ""
      ports: "8888/http"
      volumeMountPath: "/workspace"
      env: [{ key: "JUPYTER_PASSWORD", value: "your-password" }]
    }
  ) {
    id
    imageName
    env
    machineId
    machine {
      podHostId
    }
  }
}

{
  "data": {
    "podRentInterruptable": {
      "id": "fkjbybgpwuvmhk",
      "imageName": "runpod/pytorch",
      "env": ["JUPYTER_PASSWORD=your-password"],
      "machineId": "hpvdausak8xb",
      "machine": {
        "podHostId": "fkjbybgpwuvmhk-64410065"
      }
    }
  }
}

Filter by CUDA version

Use allowedCudaVersions to restrict Pods to machines with specific CUDA versions.

cURL
GraphQL

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{
    "query": "mutation { podFindAndDeployOnDemand( input: { cloudType: ALL, gpuCount: 1, volumeInGb: 40, containerDiskInGb: 40, gpuTypeId: \"NVIDIA RTX A6000\", name: \"Runpod Pytorch\", imageName: \"runpod/pytorch\", allowedCudaVersions: [\"12.0\", \"12.1\", \"12.2\", \"12.3\"] } ) { id imageName machineId } }"
  }'

mutation {
  podFindAndDeployOnDemand(
    input: {
      cloudType: ALL
      gpuCount: 1
      volumeInGb: 40
      containerDiskInGb: 40
      gpuTypeId: "NVIDIA RTX A6000"
      name: "Runpod Pytorch"
      imageName: "runpod/pytorch"
      allowedCudaVersions: ["12.0", "12.1", "12.2", "12.3"]
    }
  ) {
    id
    imageName
    machineId
  }
}

Start a Pod

Resume a stopped Pod. Use podResume for on-demand Pods or podBidResume for spot Pods.

On-demand Pod

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "mutation { podResume( input: { podId: \"YOUR_POD_ID\", gpuCount: 1 } ) { id desiredStatus imageName } }"}'

mutation {
  podResume(input: { podId: "YOUR_POD_ID", gpuCount: 1 }) {
    id
    desiredStatus
    imageName
  }
}

{
  "data": {
    "podResume": {
      "id": "YOUR_POD_ID",
      "desiredStatus": "RUNNING",
      "imageName": "runpod/tensorflow"
    }
  }
}

You can also filter by CUDA version when starting a Pod:

mutation {
  podResume(input: {
    podId: "YOUR_POD_ID",
    gpuCount: 1,
    allowedCudaVersions: ["12.0", "12.1", "12.2", "12.3"]
  }) {
    id
    desiredStatus
  }
}

Spot Pod

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "mutation { podBidResume( input: { podId: \"YOUR_POD_ID\", bidPerGpu: 0.2, gpuCount: 1 } ) { id desiredStatus imageName } }"}'

mutation {
  podBidResume(input: { podId: "YOUR_POD_ID", bidPerGpu: 0.2, gpuCount: 1 }) {
    id
    desiredStatus
    imageName
  }
}

{
  "data": {
    "podBidResume": {
      "id": "YOUR_POD_ID",
      "desiredStatus": "RUNNING",
      "imageName": "runpod/tensorflow"
    }
  }
}

Stop a Pod

Stopping a Pod releases the GPU while preserving your volume data.

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "mutation { podStop(input: {podId: \"YOUR_POD_ID\"}) { id desiredStatus } }"}'

mutation {
  podStop(input: { podId: "YOUR_POD_ID" }) {
    id
    desiredStatus
  }
}

{
  "data": {
    "podStop": {
      "id": "YOUR_POD_ID",
      "desiredStatus": "EXITED"
    }
  }
}

Query Pods

List all Pods

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "query { myself { pods { id name runtime { uptimeInSeconds gpus { id gpuUtilPercent memoryUtilPercent } container { cpuPercent memoryPercent } } } } }"}'

query {
  myself {
    pods {
      id
      name
      runtime {
        uptimeInSeconds
        ports {
          ip
          isIpPublic
          privatePort
          publicPort
          type
        }
        gpus {
          id
          gpuUtilPercent
          memoryUtilPercent
        }
        container {
          cpuPercent
          memoryPercent
        }
      }
    }
  }
}

{
  "data": {
    "myself": {
      "pods": [
        {
          "id": "ldl1dxirsim64n",
          "name": "Runpod Pytorch",
          "runtime": {
            "uptimeInSeconds": 3931,
            "ports": [
              {
                "ip": "100.65.0.101",
                "isIpPublic": false,
                "privatePort": 8888,
                "publicPort": 60141,
                "type": "http"
              }
            ],
            "gpus": [
              {
                "id": "GPU-e0488b7e-6932-795b-a125-4472c16ea72c",
                "gpuUtilPercent": 0,
                "memoryUtilPercent": 0
              }
            ],
            "container": {
              "cpuPercent": 0,
              "memoryPercent": 0
            }
          }
        }
      ]
    }
  }
}

Get Pod by ID

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "query { pod(input: {podId: \"YOUR_POD_ID\"}) { id name runtime { uptimeInSeconds gpus { id gpuUtilPercent memoryUtilPercent } } } }"}'

query {
  pod(input: { podId: "YOUR_POD_ID" }) {
    id
    name
    runtime {
      uptimeInSeconds
      ports {
        ip
        isIpPublic
        privatePort
        publicPort
        type
      }
      gpus {
        id
        gpuUtilPercent
        memoryUtilPercent
      }
      container {
        cpuPercent
        memoryPercent
      }
    }
  }
}

{
  "data": {
    "pod": {
      "id": "YOUR_POD_ID",
      "name": "Runpod Pytorch",
      "runtime": {
        "uptimeInSeconds": 11,
        "ports": [
          {
            "ip": "100.65.0.101",
            "isIpPublic": false,
            "privatePort": 8888,
            "publicPort": 60141,
            "type": "http"
          }
        ],
        "gpus": [
          {
            "id": "GPU-e0488b7e-6932-795b-a125-4472c16ea72c",
            "gpuUtilPercent": 0,
            "memoryUtilPercent": 0
          }
        ],
        "container": {
          "cpuPercent": 0,
          "memoryPercent": 0
        }
      }
    }
  }
}

Query GPU types

List available GPU types to find the gpuTypeId needed when creating Pods.

List all GPU types

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "query { gpuTypes { id displayName memoryInGb } }"}'

query {
  gpuTypes {
    id
    displayName
    memoryInGb
  }
}

{
  "data": {
    "gpuTypes": [
      {
        "id": "NVIDIA GeForce RTX 3070",
        "displayName": "RTX 3070",
        "memoryInGb": 8
      },
      {
        "id": "NVIDIA GeForce RTX 3080",
        "displayName": "RTX 3080",
        "memoryInGb": 10
      },
      {
        "id": "NVIDIA RTX A6000",
        "displayName": "RTX A6000",
        "memoryInGb": 48
      }
    ]
  }
}

Get GPU type details

Query a specific GPU type to see pricing and availability.

cURL
GraphQL
Output

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "query { gpuTypes(input: {id: \"NVIDIA GeForce RTX 3090\"}) { id displayName memoryInGb secureCloud communityCloud lowestPrice(input: {gpuCount: 1}) { minimumBidPrice uninterruptablePrice } } }"}'

query {
  gpuTypes(input: { id: "NVIDIA GeForce RTX 3090" }) {
    id
    displayName
    memoryInGb
    secureCloud
    communityCloud
    lowestPrice(input: { gpuCount: 1 }) {
      minimumBidPrice
      uninterruptablePrice
    }
  }
}

{
  "data": {
    "gpuTypes": [
      {
        "id": "NVIDIA GeForce RTX 3090",
        "displayName": "RTX 3090",
        "memoryInGb": 24,
        "secureCloud": false,
        "communityCloud": true,
        "lowestPrice": {
          "minimumBidPrice": 0.163,
          "uninterruptablePrice": 0.3
        }
      }
    ]
  }
}

Check GPU availability

Use the stockStatus field to check availability before creating a Pod. Values include High, Medium, Low, and None.

cURL
GraphQL
Output (high stock)
Output (low stock)

curl --request POST \
  --header 'content-type: application/json' \
  --url 'https://api.runpod.io/graphql?api_key=${YOUR_API_KEY}' \
  --data '{"query": "query { gpuTypes(input: { id: \"NVIDIA RTX A4000\" }) { id displayName lowestPrice(input: { gpuCount: 1, secureCloud: true }) { stockStatus minimumBidPrice uninterruptablePrice availableGpuCounts } } }"}'

query {
  gpuTypes(input: { id: "NVIDIA RTX A4000" }) {
    id
    displayName
    lowestPrice(input: { gpuCount: 1, secureCloud: true }) {
      stockStatus
      minimumBidPrice
      uninterruptablePrice
      availableGpuCounts
    }
  }
}

{
  "data": {
    "gpuTypes": [
      {
        "id": "NVIDIA RTX A4000",
        "displayName": "RTX A4000",
        "lowestPrice": {
          "stockStatus": "High",
          "minimumBidPrice": 0.2,
          "uninterruptablePrice": 0.35,
          "availableGpuCounts": [1, 2, 4]
        }
      }
    ]
  }
}

{
  "data": {
    "gpuTypes": [
      {
        "id": "NVIDIA RTX A4000",
        "displayName": "RTX A4000",
        "lowestPrice": {
          "stockStatus": "Low",
          "minimumBidPrice": 0.16,
          "uninterruptablePrice": 0.24,
          "availableGpuCounts": [1, 2, 3, 4, 5, 6, 7]
        }
      }
    ]
  }
}

If stockStatus is Low, there are very few GPUs available. Consider selecting an alternative GPU type or trying again later.

Get started

Flash

Serverless

Pods

Storage

Public Endpoints

Instant Clusters

Integrations

Hub

Fine-tuning

Reference

Quick reference

Create a Pod

On-demand Pod

Spot Pod

Filter by CUDA version

Start a Pod

On-demand Pod

Spot Pod

Stop a Pod

Query Pods

List all Pods

Get Pod by ID

Query GPU types

List all GPU types

Get GPU type details

Check GPU availability

Get started

Flash

Serverless

Pods

Storage

Public Endpoints

Instant Clusters

Integrations

Hub

Fine-tuning

Reference

​Quick reference

​Create a Pod

​On-demand Pod

​Spot Pod

​Filter by CUDA version

​Start a Pod

​On-demand Pod

​Spot Pod

​Stop a Pod

​Query Pods

​List all Pods

​Get Pod by ID

​Query GPU types

​List all GPU types

​Get GPU type details

​Check GPU availability

Quick reference

Create a Pod

On-demand Pod

Spot Pod

Filter by CUDA version

Start a Pod

On-demand Pod

Spot Pod

Stop a Pod

Query Pods

List all Pods

Get Pod by ID

Query GPU types

List all GPU types

Get GPU type details

Check GPU availability