How to manage dedicated deployment using HTTP APIs
Manage your dedicated deployment using our HTTP APIs.
Notices:
All endpoints are hosted at
https://roboflow.cloud
.Check the response code:
If it's
200
, decode the response body as a JSON object.Otherwise, the response body contains an error message as a string.
POST /add — create a dedicated deployment
Request Body Example (json)
{
"api_key": API_KEY,
"deployment_name": "dev-testing",
"machine_type": "dev-gpu",
"creator_email": YOUR_EMAIL_ADDRESS,
"duration": 3.0,
"inference_version": "latest",
"min_replicas": 1,
"max_replicas": 1
}
Request Body Schema (json)
api_key (string): required
deployment_name (string): required
machine_type (string): required
creator_email (string): required
duration (float): optional, unit is hour. default is
3
inference_version (string): optional, default is
latest
min_replicas (integer): optional, default is
1
max_replicas (integer): optional, default is
1
Response Example (json)
{
"deployment_id": "IwzJ5YLQ0iDhwzqoh3Ae",
"deployment_name": "dev-testing",
"machine_type": "dev-gpu",
"creator_email": YOUR_EMAIL_ADDRESS,
"creator_id": YOUR_USER_ID,
"subdomain": "dev-testing",
"domain": "dev-testing.roboflow.cloud",
"duration": 3.0,
"inference_version": "0.45.0",
"max_replicas": 1,
"min_replicas": 1,
"num_replicas": 0,
"status": "pending",
"workspace_id": YOUR_WORKSPACE_ID,
"workspace_url": YOUR_WORKSPACE_URL
}
Response Schema (json)
deployment_id (string): an unique identifier
deployment_name (string)
machine_type (string)
creator_email (string)
creator_id (string): the user id corresponding to
creator_email
subdomain (string): not always the same as
deployment_name
, we'll add some suffix if the subdomain is already takendomain (string)
duration (float)
inference_version (string)
min_replicas (integer)
max_replicas (integer)
num_replicas (integer): current available replicas
status (string)
workspace_id (string)
workspace_url (string)
GET /list — list dedicated deployments in your workspace
Query Parameters
api_key (string): required
show_expired (string): optional, default is
false
show_deleted (string): optional, default is
false
Response Example (json)
[
{
"deployment_id": "IwzJ5YLQ0iDhwzqoh3Ae",
"deployment_name": "dev-testing",
"machine_type": "dev-gpu",
"creator_email": YOUR_EMAIL_ADDRESS,
"creator_id": YOUR_USER_ID,
"subdomain": "dev-testing",
"domain": "dev-testing.roboflow.cloud",
"duration": 3.0,
"inference_version": "0.45.0",
"max_replicas": 1,
"min_replicas": 1,
"num_replicas": 0,
"status": "pending",
"workspace_id": YOUR_WORKSPACE_ID,
"workspace_url": YOUR_WORKSPACE_URL
}
]
Response Schema (json)
a list of dedicated deployment entries, while each entry has the same schema as describe in the /add endpoint.
GET /get — get details of a dedicated deployment
Query Parameters
api_key (string): required
deployment_name (string): required
Response Example (json)
{
"deployment_id": "IwzJ5YLQ0iDhwzqoh3Ae",
"deployment_name": "dev-testing",
"machine_type": "dev-gpu",
"creator_email": YOUR_EMAIL_ADDRESS,
"creator_id": YOUR_USER_ID,
"subdomain": "dev-testing",
"domain": "dev-testing.roboflow.cloud",
"duration": 3.0,
"inference_version": "0.45.0",
"max_replicas": 1,
"min_replicas": 1,
"num_replicas": 0,
"status": "pending",
"workspace_id": YOUR_WORKSPACE_ID,
"workspace_url": YOUR_WORKSPACE_URL
}
Response Schema (json)
the same schema as the response of the /add endpoint.
GET /get_log — get logs of a dedicated deployment
Query Parameters
api_key (string): required
deployment_name (string): required
max_entries (integer): optional, default is 50
from_timestamp (string): optional, in ISO 8601 format, default is 1 hour before current time
to_timestamp (string): optional, in ISO 8601 format, default is current time
Response Example (json)
[
{
"insert_id": "gpwrgrw55p7b9jdq",
"payload": "INFO: 10.18.0.38:46296 - \"GET /info HTTP/1.1\" 200 OK",
"severity": "INFO",
"timestamp": "2025-01-22T13:23:14.209436+00:00"
},
{
"insert_id": "mbieh16zdjvqp81j",
"payload": "INFO: 10.18.0.38:46294 - \"GET /info HTTP/1.1\" 200 OK",
"severity": "INFO",
"timestamp": "2025-01-22T13:23:14.208738+00:00"
},
{
"insert_id": "0odfnfwh8ts6e4jt",
"payload": "INFO: 10.18.0.38:54650 - \"GET /info HTTP/1.1\" 200 OK",
"severity": "INFO",
"timestamp": "2025-01-22T13:22:14.209054+00:00"
},
{
"insert_id": "s3nabhyhejuke6ub",
"payload": "INFO: 10.18.0.38:54640 - \"GET /info HTTP/1.1\" 200 OK",
"severity": "INFO",
"timestamp": "2025-01-22T13:22:14.208329+00:00"
},
{
"insert_id": "2cz5u3jx4ma22tl8",
"payload": "INFO: 10.18.0.38:40264 - \"GET /info HTTP/1.1\" 200 OK",
"severity": "INFO",
"timestamp": "2025-01-22T13:21:14.209900+00:00"
}
]
Response Schema (json)
a list of log entries, while each entry has following attributes:
insert_id (string): unique identifier for each log entry
payload (string): log content
severity (string)
timestamp (string)
POST /pause — pause a dedicated deployment
Request Body Example (json)
{
"api_key": API_KEY,
"deployment_name": "dev-testing"
}
Request Body Schema (json)
api_key (string): required
deployment_name (string): require
Response Example (json)
{
"message": "OK"
}
Response Schema
message (string)
Last updated
Was this helpful?