Why "costPerHr" in /v1/endpoints differs so much from the actual cost per hour?

it says that cost of running NVIDIA A100 80GB PCIe is $1.64 per hour, which is a lie because it is actually $2.736 per hour. Also there is no name of the GPU the worker is running on GET /v1/endpoints
{
"createdAt":"2025-05-02T07:18:46.953Z",
"executionTimeoutMs":600000,
"flashboot":false,
"gpuCount":1,
"gpuTypeIds":[
"NVIDIA A100 80GB PCIe",
"NVIDIA A100-SXM4-80GB",
"NVIDIA H100 PCIe",
"NVIDIA H100 80GB HBM3"
],
"id":"n6wtc0qo7ntn3v",
"idleTimeout":5,
"name":"live preview",
"networkVolumeId":"",
"scalerType":"QUEUE_DELAY",
"scalerValue":4,
"templateId":"r7vfrhnsx1",
"userId":"user_2qgGEbsTKEyi5u7Hxm5MfEXThMu",
"version":5,
"workers":[
{
"aiApiId":"n6wtc0qo7ntn3v",
"consumerUserId":"user_2qgGEbsTKEyi5u7Hxm5MfEXThMu",
"containerDiskInGb":65,
"costPerHr":1.64,
"createdAt":"2025-05-08 13:34:22.85 +0000 UTC",
"desiredStatus":"EXITED",
"endpointId":"n6wtc0qo7ntn3v",
"env":{
...
"RUNPOD_DEBUG_LEVEL":"INFO",
"RUNPOD_ENDPOINT_ID":"n6wtc0qo7ntn3v",
"RUNPOD_GPU_SIZE":"AMPERE_80,ADA_80_PRO,HOPPER_141",
"RUNPOD_PING_INTERVAL":"4000",
...
},
"gpuCount":1,
"id":"cq95dwnrbf13cu",
"imageName":"neykuratick001/runpod-migrate:18",
"lastStartedAt":"2025-05-08 13:39:08.133 +0000 UTC",
"lastStatusChange":"Exited by RunPod: Thu May 08 2025 13:47:09 GMT+0000 (Coordinated Universal Time)",
"machine":{

},
"machineId":"fzcgeamp5sfc",
"memoryInGb":117,
"name":"n6wtc0qo7ntn3v",
"portMappings":null,
"publicIp":"",
"slsVersion":5,
"templateId":"r7vfrhnsx1",
"vcpuCount":31,
"volumeInGb":0,
"volumeMountPath":"/runpod-volume"
}
],
"workersMax":3,
"workersMin":0,
"workersStandby":3
}
{
"createdAt":"2025-05-02T07:18:46.953Z",
"executionTimeoutMs":600000,
"flashboot":false,
"gpuCount":1,
"gpuTypeIds":[
"NVIDIA A100 80GB PCIe",
"NVIDIA A100-SXM4-80GB",
"NVIDIA H100 PCIe",
"NVIDIA H100 80GB HBM3"
],
"id":"n6wtc0qo7ntn3v",
"idleTimeout":5,
"name":"live preview",
"networkVolumeId":"",
"scalerType":"QUEUE_DELAY",
"scalerValue":4,
"templateId":"r7vfrhnsx1",
"userId":"user_2qgGEbsTKEyi5u7Hxm5MfEXThMu",
"version":5,
"workers":[
{
"aiApiId":"n6wtc0qo7ntn3v",
"consumerUserId":"user_2qgGEbsTKEyi5u7Hxm5MfEXThMu",
"containerDiskInGb":65,
"costPerHr":1.64,
"createdAt":"2025-05-08 13:34:22.85 +0000 UTC",
"desiredStatus":"EXITED",
"endpointId":"n6wtc0qo7ntn3v",
"env":{
...
"RUNPOD_DEBUG_LEVEL":"INFO",
"RUNPOD_ENDPOINT_ID":"n6wtc0qo7ntn3v",
"RUNPOD_GPU_SIZE":"AMPERE_80,ADA_80_PRO,HOPPER_141",
"RUNPOD_PING_INTERVAL":"4000",
...
},
"gpuCount":1,
"id":"cq95dwnrbf13cu",
"imageName":"neykuratick001/runpod-migrate:18",
"lastStartedAt":"2025-05-08 13:39:08.133 +0000 UTC",
"lastStatusChange":"Exited by RunPod: Thu May 08 2025 13:47:09 GMT+0000 (Coordinated Universal Time)",
"machine":{

},
"machineId":"fzcgeamp5sfc",
"memoryInGb":117,
"name":"n6wtc0qo7ntn3v",
"portMappings":null,
"publicIp":"",
"slsVersion":5,
"templateId":"r7vfrhnsx1",
"vcpuCount":31,
"volumeInGb":0,
"volumeMountPath":"/runpod-volume"
}
],
"workersMax":3,
"workersMin":0,
"workersStandby":3
}
1 Reply
U forgot ur spanish lessons
If the price difference is to be excepted, then how can i get the price of a serverless request after it's finished running? ok, apprearantly you can get gpu name by running GET on rest.runpod.io/v1/pods with includeMachine=true query. But the price is still wrong

Did you find this page helpful?