import requests
import os

model_id = ""
deployment_id = ""
# Read secrets from environment variables
baseten_api_key = os.environ["BASETEN_API_KEY"]

resp = requests.get(
    f"https://model-{model_id}.api.baseten.co/deployment/{deployment_id}/async_queue_status",
    headers={"Authorization": f"Api-Key {baseten_api_key}"}
)

print(resp.json())

{
  "model_id": "<string>",
  "deployment_id": "<string>",
  "num_queued_requests": 12,
  "num_in_progress_requests": 3
}

​
Parameters

​
model_id
string
required
The ID of the model.
​
deployment_id
string
required
The ID of the deployment.

​
Headers

​
Authorization
string
required
Your Baseten API key, formatted with prefix Api-Key (e.g. {"Authorization": "Api-Key abcd1234.abcd1234"}).

​
Response

​
model_id
string
required
The ID of the model.
​
deployment_id
string
required
The ID of the deployment.
​
num_queued_requests
integer
required
The number of requests in the deployment’s async queue with QUEUED status (i.e. awaiting processing by the model).
​
num_in_progress_requests
integer
required
The number of requests in the deployment’s async queue with IN_PROGRESS status (i.e. currently being processed by the model).
{
  "model_id": "<string>",
  "deployment_id": "<string>",
  "num_queued_requests": 12,
  "num_in_progress_requests": 3
}

​
Rate limits

Calls to the /async_queue_status endpoint are limited to 20 requests per second. If this limit is exceeded, subsequent requests will receive a 429 status code. To gracefully handle hitting this rate limit, we advise implementing a backpressure mechanism, such as calling /async_queue_status with exponential backoff in response to 429 errors. 
import requests
import os

model_id = ""
deployment_id = ""
# Read secrets from environment variables
baseten_api_key = os.environ["BASETEN_API_KEY"]

resp = requests.get(
    f"https://model-{model_id}.api.baseten.co/deployment/{deployment_id}/async_queue_status",
    headers={"Authorization": f"Api-Key {baseten_api_key}"}
)

print(resp.json())