Implementation:SeldonIO Seldon core Seldon Model Status

Property	Value
Implementation Name	Seldon_Model_Status
Type	External Tool Doc
Overview	Concrete CLI tool for checking the deployment status and readiness of Seldon Core 2 models.
Implements Principle	SeldonIO_Seldon_core_Model_Readiness_Verification
Workflow	Model_Deployment
Domains	MLOps, Kubernetes
Source	docs-gb/cli/seldon_model_status.md:L1-25
External Dependencies	seldon CLI, kubectl, jq
Last Updated	2026-02-13 00:00 GMT

Description

The seldon model status command queries the Seldon scheduler for the current deployment status of a model. It supports a blocking wait mode (-w) that polls until a specified condition (such as ModelAvailable) is met, making it ideal for use in deployment scripts and CI/CD pipelines. The equivalent information can be retrieved via kubectl by inspecting the status.conditions field of the Model resource.

Code Reference

Source: docs-gb/cli/seldon_model_status.md:L1-25

CLI Signature:

seldon model status <modelName> [-w ModelAvailable] [--scheduler-host string]

Alternative (kubectl):

kubectl get model <name> -o json | jq '.status.conditions[]'

Key Parameters

Parameter	Type	Default	Description
modelName	string (positional)	(required)	Name of the model to check status for
-w / --wait	string	(none)	Condition to wait for (e.g., ModelAvailable, ModelFailed)
--scheduler-host	string	"0.0.0.0:9004"	Address of the Seldon scheduler gRPC endpoint
-h / --help	boolean	false	Display help information for the command

I/O Contract

Inputs

Input	Type	Description
Model name	string	The name of a previously deployed Seldon Core 2 model

Outputs

Output	Type	Description
Status response (CLI)	JSON	Empty JSON {} on success when using the -w wait flag
Status conditions (kubectl)	JSON	Array of condition objects: {"type": "ModelAvailable", "status": "True", "reason": "...", "message": "..."}

Usage Examples

Wait for Model Readiness

# Block until the model is available for inference
seldon model status iris -w ModelAvailable

Check Status Without Waiting

# Get current status without blocking
seldon model status iris

Check Status via kubectl

# Inspect model conditions using kubectl and jq
kubectl get model iris -o json | jq '.status.conditions[]'

Example output:

{
  "type": "ModelAvailable",
  "status": "True",
  "lastTransitionTime": "2026-02-13T00:00:00Z",
  "reason": "ModelAvailable",
  "message": "Model is available"
}

Usage in a Deployment Script

# Full deployment and verification workflow
seldon model load -f samples/models/sklearn1.yaml
seldon model status iris -w ModelAvailable
echo "Model iris is ready for inference"
seldon model infer iris '{"inputs": [{"name": "predict", "shape": [1, 4], "datatype": "FP32", "data": [[5.1, 3.5, 1.4, 0.2]]}]}'

Knowledge Sources

• Repository: https://github.com/SeldonIO/seldon-core
• Documentation: https://docs.seldon.io/projects/seldon-core/en/v2/

Related Pages

• SeldonIO_Seldon_core_Seldon_Model_Status implements SeldonIO_Seldon_core_Model_Readiness_Verification
• SeldonIO_Seldon_core_Seldon_Model_Load precedes SeldonIO_Seldon_core_Seldon_Model_Status
• SeldonIO_Seldon_core_Seldon_Model_Infer follows SeldonIO_Seldon_core_Seldon_Model_Status
• Environment:SeldonIO_Seldon_core_Kubernetes_Cluster_Environment