Lytics ML Models API
The ML Models API from Lytics — 3 operation(s) for ml models.
Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/lytics-ml-models-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
contact:
email: support@lytics.com
name: Lytics Support
url: https://support.lytics.com/hc/en-us
description: Version 2 of the Lytics API
termsOfService: https://www.lytics.com/terms-of-service/
title: Lytics ML Models API
version: '2.0'
servers:
- url: https://api.lytics.io/v2
tags:
- name: ML Models
paths:
/ml:
get:
description: Get a list of all ML models for the account
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
responses:
'200':
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/models.ApiResponse'
- properties:
data:
items:
$ref: '#/components/schemas/models.MLModel'
type: array
type: object
description: ML Model List Response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Bad Request
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Get ML Models
tags:
- ML Models
post:
description: Create an ML Model
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
requestBody:
content:
'*/*':
schema:
$ref: '#/components/schemas/models.MLModel'
description: ML Model Request
required: true
x-originalParamName: model
responses:
'201':
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/models.ApiResponse'
- properties:
data:
$ref: '#/components/schemas/models.MLModel'
type: object
description: ML Model Response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Bad Request
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Post ML Model
tags:
- ML Models
/ml/{id}:
delete:
description: Delete an ML model by ID
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
- description: The model ID
in: path
name: id
required: true
schema:
type: string
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiResponse'
description: OK
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Delete ML Model
tags:
- ML Models
get:
description: Get an ML model by ID
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
- description: The model ID
in: path
name: id
required: true
schema:
type: string
responses:
'200':
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/models.ApiResponse'
- properties:
data:
$ref: '#/components/schemas/models.MLModel'
type: object
description: ML Model Response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Bad Request
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Get ML Model
tags:
- ML Models
put:
description: Update an ML model by ID
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
- description: The model ID
in: path
name: id
required: true
schema:
type: string
- description: Promote and deploy the model to users
in: query
name: is_active
schema:
type: string
- description: Label of the model
in: query
name: label
schema:
type: string
- description: Hide the model from the UI
in: query
name: hidden
schema:
type: string
responses:
'200':
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/models.ApiResponse'
- properties:
data:
$ref: '#/components/schemas/models.MLModel'
type: object
description: ML Model Response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Bad Request
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Update ML Model
tags:
- ML Models
/ml/{id}/summary:
get:
description: Get an ML model's summary by ID
parameters:
- description: The account ID. Defaults to the user's default account.
in: query
name: account_id
schema:
type: string
- description: The model ID
in: path
name: id
required: true
schema:
type: string
responses:
'200':
content:
application/json:
schema:
allOf:
- $ref: '#/components/schemas/models.ApiResponse'
- properties:
data:
$ref: '#/components/schemas/models.MLSummaryResponse'
type: object
description: ML Model Summary Response
'400':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Bad Request
'404':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Not Found
'500':
content:
application/json:
schema:
$ref: '#/components/schemas/models.ApiErrorResponse'
description: Internal Server Error
security:
- ApiKeyAuth: []
summary: Get ML Model Summary
tags:
- ML Models
components:
schemas:
models.ModelMessage:
properties:
severity:
description: Severity level of the message; "info", "warn", "error", or "debug"
type: string
tags:
description: Tags for the message; "summary", "workflow", "autotune", "collinearity", or "verdict"
items:
type: string
type: array
text:
description: Model message
type: string
type: object
models.MLSummaryResponse:
properties:
features:
description: All features of final model build with importances and correlations of each
items:
$ref: '#/components/schemas/models.Feature'
type: array
id:
description: ID of the model
type: string
name:
description: Name of the model
type: string
state:
description: State of the model, "complete", "building", or "invalid"
type: string
summary:
$ref: '#/components/schemas/models.MLSummary'
type: object
models.ConfusionMatrix:
properties:
FalseNegative:
description: Predicted negative but actual positive
type: integer
FalsePositive:
description: Predicted positive but actual negative
type: integer
TrueNegative:
description: Predicted negative and actual negative
type: integer
TruePositive:
description: Predicted positive and actual positive
type: integer
type: object
models.ModelConfig:
properties:
additional:
description: Additional features to include in the model
items:
type: string
type: array
auto_tune:
description: Automatically search through all data fields in Lytics and build the optimized model of the best fields
type: boolean
blocked:
description: Features to exclude from the model
items:
type: string
type: array
build_only:
description: Train the model only, do not deploy
type: boolean
collect:
description: Number of samples to collect for training
type: integer
internal:
description: Internal Lytics model; not visible to users
type: boolean
re_run:
description: Re-train the model every week
type: boolean
use_content:
description: Use content affinities as features
type: boolean
use_scores:
description: Use behavioral scores as features
type: boolean
type: object
models.ApiErrorResponse:
properties:
errors:
description: Lytics API Errors
items:
$ref: '#/components/schemas/lioerrors.ApiV2ErrorOut'
type: array
request_id:
type: string
status:
description: HTTP Status Code
type: integer
type: object
models.MLSummary:
properties:
accuracy:
description: Measure of 0-10 of how accurate the model is. Interpreted from the R-squared
type: integer
auc:
description: '"Area under curve" (0-1) for the ROC (receiver operating characteristic curve). AUC provides an overall measure of performance across all possible thresholds'
type: number
audience_similarity:
description: Jaccard Index/Similarity for source and target segments for a model
type: number
error_matrix:
$ref: '#/components/schemas/models.ConfusionMatrix'
model_health:
description: Health of the model; "healthy" or "unhealthy". Unhealthy models are not accurate enough or encountered an error during training
type: string
mse:
description: Mean squared error is the average squared difference between the estimated values and the actual value
type: number
msgs:
description: Messages to help debug and improve the model
items:
$ref: '#/components/schemas/models.ModelMessage'
type: array
reach:
description: Measure of 0-10 of how many users this model can reach. Interpreted from the False Positive Rate
type: integer
rsq:
description: R-squared is a measure (0-1) of "goodness of fit", i.e. how well the model fits the data
type: number
source_predictions:
additionalProperties:
type: integer
description: Test dataset predictions for the source audience
type: object
target_predictions:
additionalProperties:
type: integer
description: Test dataset predictions for the target audience
type: object
threshold:
description: Computed as the optimal threshold to use when creating predictive audiences. The value that optimizes both reach and accuracy simultaneously
type: number
type: object
models.Impact:
properties:
lift:
description: '%increase in the target audience when the feature is present'
type: number
threshold:
description: For numeric fields; use for determining lift
type: number
value:
description: For categorical fields
type: string
type: object
models.FieldPrevalence:
properties:
source:
description: Field prevalence in the source audience
type: number
target:
description: Field prevalence in the target audience
type: number
type: object
models.Feature:
properties:
correlation:
description: Correlation coeffient between the feature and the target audience
type: number
field_prevalence:
$ref: '#/components/schemas/models.FieldPrevalence'
impact:
$ref: '#/components/schemas/models.Impact'
importance:
description: Feature importance as calculated by the model
type: number
kind:
description: Kind of the feature; segment, lql, score, content, campaign, or unknown
type: string
name:
description: Name of the feature/data field
type: string
type:
description: Type of the feature; numeric or categorical
type: string
type: object
lioerrors.ApiV2ErrorOut:
properties:
code:
description: Lytics Error Code
enum:
- UNKNOWN-000
- BADREQ-001
- JOB-BADREQ-002
- NOTFOUND-003
- JOB-NOTFOUND-004
- WF-NOTFOUND-005
- AUTH-NOTFOUND-006
- AUTHTYPE-NOTFOUND-007
- AUTH-BADREQ-008
- TABLE-NOTFOUND-009
- SCHEMA-NOTFOUND-010
- SCHEMAVERSION-NOTFOUND-011
- ENTITY-NOTFOUND-012
- QUERY-NOTFOUND-013
- STREAM-NOTFOUND-014
- PROVIDER-BADREQ-015
- PROVIDER-NOTFOUND-016
- UNAUTHORIZED-017
- SCHEMA-INVALID-018
- INTERNAL-019
- ROUTERULE-NOTFOUND-020
- ACCOUNT-NOTFOUND-021
- JOB-FAULT-022
- USER-NOTFOUND-023
- USER-BADREQ-024
- JSON-BADREQ-025
- FORBIDDEN-026
type: string
level:
description: When the error was generated
type: string
message:
description: A description of the error that occurred
type: string
timestamp:
description: The time the error occurred
format: date-time
type: string
type: object
models.ApiResponse:
properties:
_meta:
additionalProperties: true
description: Response Metadata
type: object
data:
description: Response Payload
type: object
request_id:
type: string
status:
description: HTTP Status Code
type: integer
type: object
models.MLModel:
properties:
additional_data:
additionalProperties:
type: string
type: object
aid:
type: integer
author_id:
description: Creator of the model
type: string
config:
$ref: '#/components/schemas/models.ModelConfig'
created:
description: Created timestamp
type: string
description:
description: Description for the model
type: string
error:
description: Error from model training; set to nil if no error or "building" if model is still training
type: string
hidden:
description: Model is hidden from the UI
type: boolean
id:
description: ID of the model
type: string
is_active:
description: Has model been promoted and deployed to users
type: boolean
is_healthy:
description: Model health
type: boolean
label:
description: Label for the model
type: string
name:
description: Name of the model
type: string
source:
description: Source segment ID of the model
type: string
state:
description: State of the model, "complete", "building", or "invalid"
type: string
target:
description: Target segment ID of the model
type: string
type:
description: Model algorithm chosen from automatic tuning; random forest (rf), logistic regression (lr), or gradient boosting machine (gbm)
type: string
updated:
description: Updated timestamp for re-training
type: string
work_ids:
description: Work IDs of the model; presence of multiple usually indicates an eval-only work, thus the model has been deployed at one point
items:
type: string
type: array
type: object
securitySchemes:
ApiKeyAuth:
in: header
name: Authorization
type: apiKey