CreateInferenceV3DeploymentRequest.md

CreateInferenceV3DeploymentRequest

Properties

Name	Type	Description	Notes
max_surge	int		[optional]
max_unavailable	int		[optional]
name	str
cluster_id	int
hardware_instance_id	int
user_annotations	Dict[str, str]		[optional]
image_url	str
image_pull_secret_credentials	ImagePullSecretCredentials		[optional]
port	int
min_replicas	int
max_replicas	int
initial_replicas	int		[optional]
concurrency	int		[optional]
cooldown_period	int		[optional]
healthcheck	str		[optional]
env_vars	Dict[str, str]		[optional]
command	str		[optional]
endpoint_bearer_token	str		[optional]
endpoint_certificate_authority	str		[optional]
hf_token	str		[optional]
backend_protocol	BackendProtocol		[optional]
enable_logging	bool		[optional] [default to False]
session_affinity	bool	Enable best-effort sticky routing via the `X-Session-Id` request header. Requests carrying the same header value land on the same pod, improving KV cache reuse for agentic workloads. Requests without the header are routed at random. Affinity is NOT durable: scaling, rollouts, restarts, or readiness-probe transitions will remap sessions to different pods. Do not use for irreplaceable in-pod state.	[optional] [default to False]
config_file	ConfigFileMount		[optional]

Example

from platform_api_python_client.models.create_inference_v3_deployment_request import CreateInferenceV3DeploymentRequest

# TODO update the JSON string below
json = "{}"
# create an instance of CreateInferenceV3DeploymentRequest from a JSON string
create_inference_v3_deployment_request_instance = CreateInferenceV3DeploymentRequest.from_json(json)
# print the JSON string representation of the object
print(CreateInferenceV3DeploymentRequest.to_json())

# convert the object into a dict
create_inference_v3_deployment_request_dict = create_inference_v3_deployment_request_instance.to_dict()
# create an instance of CreateInferenceV3DeploymentRequest from a dict
create_inference_v3_deployment_request_from_dict = CreateInferenceV3DeploymentRequest.from_dict(create_inference_v3_deployment_request_dict)

[Back to Model list] [Back to API list] [Back to README]