Kata.ai Prediction API
Run entity prediction against a deployed NLU model.
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/kataai-prediction-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:
title: Kata.ai NL Prediction API
description: The Kata.ai Natural Language (NL) Prediction API exposes a trained Natural Language Understanding model built in NL Studio so it can be called from any application. Given an input sentence it returns detected entities (trait, dict, phrase) with scores, spans, resolved values, and entity relationships. Reconstructed from the published Kata Platform documentation (kata-ai/kata-platform-docs, nl-studio/nl-prediction-api); an API Evangelist derived specification, not a Kata.ai-published OpenAPI.
version: 1.0.0
contact:
name: Kata.ai
email: business@kata.ai
url: https://docs.kata.ai/nl-studio/nl-prediction-api
x-provenance:
generated: '2026-07-19'
method: generated
source: https://github.com/kata-ai/kata-platform-docs/blob/master/docs/nl-studio/nl-prediction-api.md
servers:
- url: https://geist.kata.ai
description: Kata.ai NL Prediction API host
security:
- bearerAuth: []
tags:
- name: Prediction
description: Run entity prediction against a deployed NLU model.
paths:
/nlus/{nluId}/predict:
post:
tags:
- Prediction
operationId: predict
summary: Predict entities for a sentence
description: Runs the deployed NLU model identified by nluId against the input text and returns detected entities grouped by entity name. Obtain the API token from NL Studio > Settings.
parameters:
- name: nluId
in: path
required: true
schema:
type: string
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- text
properties:
text:
type: string
example: ada satu bebek dan lima kucing di sawah
responses:
'200':
description: Prediction result
content:
application/json:
schema:
$ref: '#/components/schemas/PredictionResult'
example:
result:
ner:
- type: phrase
score: 0.9999965645021311
value: sawah
label: LOCATION
start: 34
end: 39
animal:
- type: dict
score: 0.7501584501364904
value: bebek
start: 9
end: 14
resolved:
dictKey: duck
'403':
description: You're not authorized to view this page.
components:
schemas:
Entity:
type: object
properties:
type:
type: string
enum:
- trait
- dict
- phrase
start:
type: integer
end:
type: integer
score:
type: number
value:
type: string
label:
type: string
belongsTo:
type: object
properties:
name:
type: string
index:
type: integer
score:
type: number
resolved:
type: object
additionalProperties: true
PredictionResult:
type: object
properties:
result:
type: object
additionalProperties:
type: array
items:
$ref: '#/components/schemas/Entity'
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: 'Bearer token from NL Studio Settings (Authorization: Bearer <token>).'