Qlik Machine Learning API
Generate profile insights, create and manage ML experiments, deploy models, and run predictions in Qlik Cloud.
Qlik Machine Learning API is one of 82 APIs that Qlik Sense APIs publishes on the APIs.io network, described by a machine-readable OpenAPI specification.
Tagged areas include Artificial Intelligence, Machine-Learning, Predictions, and REST. The published artifact set on APIs.io includes API documentation, an API reference, and an OpenAPI specification.
This API exposes 42 operations across 24 paths, organized into 6 resource areas, and defines 134 schemas. It is described by OpenAPI 3.0.0.
Requests are made against a single base URL, https://{tenant}.{region}.qlikcloud.com.
42 operations
24 paths
134 schemas
6 DELETE14 GET6 PATCH15 POST1 PUT
Metadata
The identity and technical contract details declared by the specification.
Paths & Operations 42
Across 24 paths, the API surfaces 42 operations — 6 DELETE, 14 GET, 6 PATCH, 15 POST, 1 PUT. They span 6 resource areas: deployments, aliases, predictions, experiments, jobs, profile-insights. Each is listed below with its method, path, parameters, and response codes.
deployments 9
GET
/api/v1/ml/deployments
List deployments
POST
/api/v1/ml/deployments
Create a deployment
GET
/api/v1/ml/deployments/{deploymentId}
Get a deployment
PATCH
/api/v1/ml/deployments/{deploymentId}
Update a deployment
DELETE
/api/v1/ml/deployments/{deploymentId}
Delete a deployment
POST
/api/v1/ml/deployments/{deploymentId}/actions/activate-models
Activate the model for this deployment
POST
/api/v1/ml/deployments/{deploymentId}/actions/deactivate-models
Deactivate the model for this deployment
POST
/api/v1/ml/deployments/{deploymentId}/models/actions/add
Add deployed models for this deployment
POST
/api/v1/ml/deployments/{deploymentId}/models/actions/remove
Remove deployed models from this deployment
aliases 5
GET
/api/v1/ml/deployments/{deploymentId}/aliases
List aliases
POST
/api/v1/ml/deployments/{deploymentId}/aliases
Create an alias
GET
/api/v1/ml/deployments/{deploymentId}/aliases/{aliasId}
Get an alias
PATCH
/api/v1/ml/deployments/{deploymentId}/aliases/{aliasId}
Update an alias
DELETE
/api/v1/ml/deployments/{deploymentId}/aliases/{aliasId}
Delete an alias
predictions 12
POST
/api/v1/ml/deployments/{deploymentId}/aliases/{aliasName}/realtime-predictions/actions/run
Generate predictions in a synchronous request/response
GET
/api/v1/ml/deployments/{deploymentId}/batch-predictions
List batch prediction configurations
POST
/api/v1/ml/deployments/{deploymentId}/batch-predictions
Create a prediction configuration
GET
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}
Retrieve a batch prediction
PATCH
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}
Updates a batch prediction
DELETE
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}
Delete a batch prediction
POST
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}/actions/predict
Run a batch prediction
GET
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}/schedule
Get a batch prediction schedule
PATCH
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}/schedule
Update a batch prediction schedule
PUT
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}/schedule
Add a batch prediction schedule
DELETE
/api/v1/ml/deployments/{deploymentId}/batch-predictions/{batchPredictionId}/schedule
Delete a batch prediction schedule
POST
/api/v1/ml/deployments/{deploymentId}/realtime-predictions/actions/run
Generate predictions in a synchronous request/response
experiments 13
GET
/api/v1/ml/experiments
List experiments
POST
/api/v1/ml/experiments
Create an experiment
GET
/api/v1/ml/experiments/{experimentId}
Get an experiment
PATCH
/api/v1/ml/experiments/{experimentId}
Update an experiment
DELETE
/api/v1/ml/experiments/{experimentId}
Delete an experiment
POST
/api/v1/ml/experiments/{experimentId}/actions/recommend-models
Request model recommendations for an experiment.
GET
/api/v1/ml/experiments/{experimentId}/models
List models
GET
/api/v1/ml/experiments/{experimentId}/models/{modelId}
Get a model
GET
/api/v1/ml/experiments/{experimentId}/versions
List experiment versions
POST
/api/v1/ml/experiments/{experimentId}/versions
Create an experiment version
GET
/api/v1/ml/experiments/{experimentId}/versions/{experimentVersionId}
Get an experiment version
PATCH
/api/v1/ml/experiments/{experimentId}/versions/{experimentVersionId}
Update an experiment version
DELETE
/api/v1/ml/experiments/{experimentId}/versions/{experimentVersionId}
Delete an experiment version
jobs 1
POST
/api/v1/ml/jobs/{corrType}/{corrId}/actions/cancel
Cancel jobs
profile-insights 2
POST
/api/v1/ml/profile-insights
Start profile insights creation
GET
/api/v1/ml/profile-insights/{dataSetId}
Get profile insights
Schemas 134
The contract defines 134 schemas that model the data the API accepts and returns. The most detailed are FieldProfile (33 properties), ModelMetricsBinary (32 properties), ExperimentVersion (24 properties), Model (23 properties). Each schema is shown below with its type and property counts.
Alias
object
An AutoML alias
8 properties
8 required
AliasFindResponse
object
3 properties
2 required
AliasGetResponse
object
1 property
1 required
AliasId
string
ID of an alias
AliasInput
object
Input for creating a new alias
1 property
1 required
AliasMode
string
The mode of an alias. Default mode means the model assigned to that alias will be used if alias is not specified
AliasPatch
array
AliasPatchItem
object
Alias values that can be patched.
3 properties
3 required
AliasPostResponse
object
1 property
1 required
AnyType
Use for fields that can be any type (string, number, etc.)
APIError
object
An error object
4 properties
2 required
BatchPrediction
object
A batch prediction job configuration
17 properties
BatchPredictionActionResponse
object
Response for batch prediction predict action that indicates job and status
1 property
1 required
BatchPredictionFindResponse
object
3 properties
2 required
BatchPredictionGetResponse
object
1 property
1 required
BatchPredictionInput
object
Input values for creating a batch prediction configuration
1 property
BatchPredictionPatch
array
BatchPredictionPostResponse
object
1 property
1 required
BatchPredictionSchedule
object
Batch prediction job schedule
9 properties
BatchPredictionScheduleGetResponse
object
1 property
1 required
BatchPredictionScheduleInput
object
Input values for a batch prediction schedule
1 property
BatchPredictionScheduleInputAttributes
object
Configuration to schedule a batch prediction
5 properties
4 required
BatchPredictionSchedulePatch
array
BatchPredictionSchedulePutResponse
object
1 property
1 required
BatchPredictionStatus
string
Status of this batch prediction
BatchPredictionWriteback
object
Sets which files, file names, and spaces are used to write results of batch predictions (output files) to the catalog. Note that for predictions based on time…
7 properties
3 required
BinaryImbalanceSampling
object
3 properties
BinnedFrequency
object
A frequency bin in a field's frequency distribution.
2 properties
ChangeType
string
Indicates if you want to change the featureType for this feature within the experiment version
ColumnTransform
object
2 properties
2 required
CorrId
string
The ID of a correlated resource of corrType
CorrType
string
Types names of correlated resources (batch 'prediction' and experimentversion)
CreatedAt
string
Timestamp when this was created
CreatedBy
string
ID of the owner/user that created this entity.
DataSetId
string
The Qlik catalog dataset ID
DatasetOrigin
string
Whether this is a new or other dataset
DataSetProfile
object
Full dataset profile from the Profile Service.
3 properties
1 required
DataType
string
The data type of this feature in your dataset
DateIndexes
array
A optional date column name to index
DeletedAt
string
Timestamp when this is deleted
DeployedModelIds
array
IDs of all models deployed to the deployment
DeployedModelsInput
object
Input values for adding deployed models to a deployment
1 property
1 required
Deployment
object
A deployed model against which you can run predictions
14 properties
11 required
DeploymentFindResponse
object
3 properties
2 required
DeploymentGetResponse
object
1 property
1 required
DeploymentId
string
ID of a model deployment
DeploymentInput
object
Input for creating a new deployment
1 property
DeploymentPatch
array
DeploymentPostResponse
object
1 property
1 required
DroppedFeature
object
Feature dropped during preprocessing
2 properties
EntityDescription
string
Description of this entity
EntityId
string
ID of this entity
EntityName
string
Name of this entity
EnumSortAliases
string
EnumSortBatchPredictions
string
EnumSortDeployments
string
EnumSortExperiments
string
EnumSortExperimentVersions
string
EnumSortModels
string
ErrorMessage
string
JSON string of error object
Errors
array
JSON string with list of error objects
Experiment
object
An AutoML experiment
8 properties
6 required
ExperimentFindResponse
object
3 properties
2 required
ExperimentGetResponse
object
1 property
1 required
ExperimentId
string
ID of the experiment
ExperimentInput
object
Input for creating this entity
1 property
ExperimentMode
string
The model training mode for the experiment version
ExperimentModelRecommendationFilter
object
Criteria to determine which pool of models to provide recommendations from
4 properties
ExperimentModelRecommendationPostResponse
object
1 property
1 required
ExperimentPatch
array
ExperimentPatchItem
object
Experiment fields that can be patched. The following paths all require value to be a string: /name, /spaceId, and /description
3 properties
3 required
ExperimentPostResponse
object
1 property
1 required
ExperimentType
string
Experiment type
ExperimentVersion
object
An AutoML experiment version. This is a configuration for training models within an experiment.
24 properties
9 required
ExperimentVersionFindResponse
object
3 properties
2 required
ExperimentVersionGetResponse
object
1 property
1 required
ExperimentVersionId
string
ID of the experiment version
ExperimentVersionInput
object
Input for creating a new experiment version. Defaults provided in the ProfileInsights response.
1 property
1 required
ExperimentVersionPatch
array
ExperimentVersionPostResponse
object
1 property
1 required
Failure
object
2 properties
1 required
Feature
object
A feature (column) from your dataset
6 properties
FeatureInsights
object
Metadata about the features in your dataset, generated when you create ProfileInsights.
8 properties
5 required
FeaturesList
array
List of features from your dataset for creating Experiment Versions. This appears in from ProfileInsights response (in the defaultVersionConfig). You can adjus…
FeatureType
string
The default feature type based on the feature's data type. If you want a value to be interpreted differently (e.g. 0/1 as categorical/boolean instead of numeri…
FieldProfile
object
Profile metadata for a single field/column.
33 properties
FileType
string
Dataset file type
FindResponseMeta
object
Meta for FIND operations
1 property
1 required
IncludeProfileInsightsField
string
Fields to include in the response. Currently only supported value is dataSetProfile. When dataSetProfile is specified, the response includes the full dataset p…
IndexColumn
string
A optional column name upon which to create an index. Must be unique for every row. If not included, Qlik will create a unique index column.
Insights
string
Insights about a feature, such as why it's not included in a model
JobType
string
The type for this job
Model
object
A model based on an algorithm within an experiment version.
23 properties
ModelAlgorithm
string
Enumeration of model algorithms. A subset of these may be provided based on your ExperimentType. This is based on your target's featureType. When you select a…
ModelAlgorithmAbbreviation
string
Model algorithm name abbreviation
ModelFindResponse
object
3 properties
2 required
ModelForRecommendations
ModelGetResponse
object
1 property
1 required
ModelId
string
ID of the model
ModelInfo
object
Model information stored on an alias
1 property
ModelMetrics
object
Model metrics based on the type of model
4 properties
ModelMetricsBinary
object
Binary metrics for categorical values with two options. Details: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/SenseHub/AutoML/scoring-bina…
32 properties
ModelMetricsMulticlass
object
Multiclass metrics for categorical values with 3+ options. Details: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/SenseHub/AutoML/scoring-m…
10 properties
ModelMetricsRegression
object
Regression metrics for numeric values. Details: https://help.qlik.com/en-US/cloud-services/Subsystems/Hub/Content/SenseHub/AutoML/scoring-regression.htm
8 properties
ModelMetricsTimeseries
object
Timeseries metrics experiments valid for timeseries forecasting.
18 properties
ModelsInfo
array
ModelState
string
Model state. These are the state of the model in relation to deployments.
ModelStatus
string
Model status. These are the status of the model in relation to experiments (i.e. training status).
OutputFile
object
5 properties
5 required
OwnerId
string
ID of owner/user for this entity
ParentJobId
string
ID of the current job's parent
Pipeline
object
Pipeline metadata including transformations to apply to columns and specific schema configuration data
1 property
PredictionJobResponse
object
20 properties
20 required
PreprocessedInsightColumn
object
Metadata about features/columns from dataset after preprocessing
3 properties
3 required
ProfileClassification
object
Classification metadata for a field.
4 properties
ProfileClassificationTag
object
A classification tag with a confidence score.
2 properties
ProfileFrequency
object
A value and its frequency count.
2 properties
ProfileInsights
object
Insights (metadata) about an experiment dataset
11 properties
4 required
ProfileInsightsGetResponse
object
1 property
1 required
ProfileInsightsInput
object
Input to get dataset and feature metadata needed to create experiment versions
1 property
ProfileMetadata
object
Metadata about a dataset profile computation.
9 properties
2 required
RealtimePrediction
object
Input values for creating realtime predictions
1 property
RealtimePredictionInput
object
Input values for creating realtime predictions
2 properties
RealTimePredictionInputSchema
object
1 property
RealTimePredictionSchema
object
1 property
ResponseLinks
object
Resource links included in paginated responses
5 properties
5 required
SpaceId
string
Space ID for this entity (empty string for personal space)
TableProfile
object
Profile metadata for a single table/dataset.
4 properties
3 required
TableRecord
object
A single record of sample values.
1 property
TableSample
object
Sample values from a table/dataset.
3 properties
TenantId
string
Tenant ID for this entity
TrainingDuration
integer
Optional training duration in seconds. If not provided, max value used. If provided, min 900 (15m) and max 21600 (6h).
Transform
object
1 property
2 required
UpdatedAt
string
Timestamp when this was updated
Specification
The full machine-readable OpenAPI contract behind this narrative.
Source
More from Qlik Sense APIs 12
Other APIs Qlik Sense APIs publishes across the network.
Qlik Engine API
Qlik Server-Side Extension Protocol
Qlik Cloud System Events
Qlik MCP Server
Qlik Apps API
Qlik Change stores API
Qlik Adaptive cards API
Qlik ODAG apps API
Qlik ODAG links API
Qlik ODAG requests API
Qlik ODAG settings API
Qlik API keys API
#Artificial Intelligence#Machine-Learning#Predictions#REST
Where this information came from
This is an independent, third-party profile of Qlik Machine Learning API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.