Everywhere Inference
List inference deployments
get/cloud/v3/inference/{project_id}/deployments
Path parameters
project_idinteger required
Project ID
Example:1
Project ID
Query parameters
limitinteger
Optional. Limit the number of returned items
Example:1000
Optional. Limit the number of returned items
offsetinteger
Optional. Offset value is used to exclude the first set of records from the result
Optional. Offset value is used to exclude the first set of records from the result
Response
OK
Example response
{
"count": 1,
"results": [
{
"address": "https://example.com",
"api_keys": [
"key1",
"key2"
],
"containers": [
{
"address": "https://example.com",
"deploy_status": {
"ready": 1,
"total": 2
},
"error_message": "Failed to pull image",
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"polling_interval": 30,
"triggers": {
"cpu": {
"threshold": 75
},
"gpu_memory": {
"threshold": 75
},
"gpu_utilization": {
"threshold": 75
},
"http": {
"rate": 1,
"window": 60
},
"memory": {
"threshold": 75
},
"sqs": {
"activation_queue_length": 5,
"aws_region": "us-east-1",
"queue_length": 10,
"queue_url": "https://sqs.us-east-1.amazonaws.com/123456789012/MyQueue",
"scale_on_delayed": true,
"scale_on_flight": true
}
}
}
}
],
"created_at": "2023-08-22T11:21:00Z",
"credentials_name": "dockerhub",
"description": "My first instance",
"envs": {
"DEBUG_MODE": "False",
"KEY": "12345"
},
"flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
"image": "nginx:latest",
"ingress_opts": {
"disable_response_buffering": true
},
"listening_port": 8080,
"logging": {
"destination_region_id": 1,
"enabled": true,
"retention_policy": {
"period": 45
},
"topic_name": "my-log-name"
},
"name": "my-instance",
"object_references": [
{
"name": "my-inference-app"
}
],
"probes": {
"liveness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"port": 80,
"schema": "HTTP"
},
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"readiness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"port": 80,
"schema": "HTTP"
},
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"startup_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"port": 80,
"schema": "HTTP"
},
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
}
},
"project_id": 1,
"timeout": 120
}
]
}