Get trained models usage info

  • GET /_ml/trained_models/{model_id}/_stats
  • GET /_ml/trained_models/_stats
Auth

You can get usage information for multiple trained models in a single API request by using a comma-separated list of model IDs or a wildcard expression.

Required authorization

Cluster privileges monitor_ml

Path parameters

model_id union string | string[] optional

The unique identifier of the trained model or a model alias. It can be a comma-separated list or a wildcard expression.

Leave it out to use /_ml/trained_models/_stats.

Query parameters

allow_no_match boolean · default: true

Specifies what to do when the request:

  • Contains wildcard expressions and there are no models that match.
  • Contains the _all string or no identifiers and there are no matches.
  • Contains wildcard expressions and there are only partial matches.

If true, it returns an empty array when there are no matches and the subset of results when there are partial matches.

from number · default: 0

Skips the specified number of models.

size number · default: 100

Specifies the maximum number of models to obtain.

Response

application/json
count number required

The total number of trained model statistics that matched the requested ID patterns. Could be higher than the number of items in the trained_model_stats array as the size of the array is restricted by the supplied size parameter.

trained_model_stats object[] required

An array of trained model statistics, which are sorted by the model_id value in ascending order.

deployment_stats object

A collection of deployment stats, which is present when the models are deployed.

adaptive_allocations object
enabled boolean required

If true, adaptive_allocations is enabled

min_number_of_allocations number

Specifies the minimum number of allocations to scale to. If set, it must be greater than or equal to 0. If not defined, the deployment scales to 0.

max_number_of_allocations number

Specifies the maximum number of allocations to scale to. If set, it must be greater than or equal to min_number_of_allocations.

allocation_status object

The detailed allocation status for the deployment.

allocation_count number required

The current number of nodes where the model is allocated.

state enum required

The detailed allocation state related to the nodes.

Supported values include:

  • started: The trained model is started on at least one node.
  • starting: Trained model deployment is starting but it is not yet deployed on any nodes.
  • fully_allocated: Trained model deployment has started on all valid nodes.
Values: started starting fully_allocated
target_allocation_count number required

The desired number of nodes for model allocation.

cache_size number | string
deployment_id string required

The unique identifier for the trained model deployment.

error_count number

The sum of error_count for all nodes in the deployment.

inference_count number

The sum of inference_count for all nodes in the deployment.

model_id string required

The unique identifier for the trained model.

nodes object[] required

The deployment stats for each node that currently has the model allocated. In serverless, stats are reported for a single unnamed virtual node.

average_inference_time_ms number

The average time for each inference call to complete on this node.

average_inference_time_ms_last_minute number
average_inference_time_ms_excluding_cache_hits number

The average time for each inference call to complete on this node, excluding cache

error_count number

The number of errors when evaluating the trained model.

inference_count number

The total number of inference calls made against this node for this model.

inference_cache_hit_count number
inference_cache_hit_count_last_minute number
last_access number

The epoch time stamp of the last inference call for the model on this node.

node object

Information pertaining to the node.

number_of_allocations number

The number of allocations assigned to this node.

number_of_pending_requests number

The number of inference requests queued to be processed.

peak_throughput_per_minute number required
rejected_execution_count number

The number of inference requests that were not processed because the queue was full.

routing_state object required

The current routing state and reason for the current routing state for this allocation.

reason string

The reason for the current state. It is usually populated only when the routing_state is failed.

routing_state enum required

The current routing state.

Supported values include:

  • failed: The allocation attempt failed.
  • started: The trained model is allocated and ready to accept inference requests.
  • starting: The trained model is attempting to allocate on this node; inference requests are not yet accepted.
  • stopped: The trained model is fully deallocated from this node.
  • stopping: The trained model is being deallocated from this node.
Values: failed started starting stopped stopping
start_time number

The epoch timestamp when the allocation started.

threads_per_allocation number

The number of threads used by each allocation during inference.

throughput_last_minute number required
timeout_count number

The number of inference requests that timed out before being processed.

number_of_allocations number

The number of allocations requested.

peak_throughput_per_minute number required
priority enum required
Values: normal low
queue_capacity number

The number of inference requests that can be queued before new requests are rejected.

rejected_execution_count number

The sum of rejected_execution_count for all nodes in the deployment. Individual nodes reject an inference request if the inference queue is full. The queue size is controlled by the queue_capacity setting in the start trained model deployment API.

reason string

The reason for the current deployment state. Usually only populated when the model is not deployed to a node.

start_time number required

The epoch timestamp when the deployment started.

state enum

The overall state of the deployment.

Supported values include:

  • started: The deployment is usable; at least one node has the model allocated.
  • starting: The deployment has recently started but is not yet usable; the model is not allocated on any nodes.
  • stopping: The deployment is preparing to stop and deallocate the model from the relevant nodes.
  • failed: The deployment is on a failed state and must be re-deployed.
Values: started starting stopping failed
threads_per_allocation number

The number of threads used be each allocation during inference.

timeout_count number

The sum of timeout_count for all nodes in the deployment.

inference_stats object

A collection of inference stats fields.

cache_miss_count number required

The number of times the model was loaded for inference and was not retrieved from the cache. If this number is close to the inference_count, the cache is not being appropriately used. This can be solved by increasing the cache size or its time-to-live (TTL). Refer to general machine learning settings for the appropriate settings.

failure_count number required

The number of failures when using the model for inference.

inference_count number required

The total number of times the model has been called for inference. This is across all inference contexts, including all pipelines.

missing_all_fields_count number required

The number of inference calls where all the training features for the model were missing.

timestamp number required

The time when the statistics were last updated.

ingest map string to object

A collection of ingest stats for the model across all nodes. The values are summations of the individual node statistics. The format matches the ingest section in the nodes stats API.

model_id string required

The unique identifier of the trained model.

model_size_stats object required

A collection of model size stats.

model_size_bytes number | string required

The size of the model in bytes.

required_native_memory_bytes number | string required

The amount of memory required to load the model in bytes.

pipeline_count number required

The number of ingest pipelines that currently refer to the model.