top of page

Developer quickstart

Introduction 

This API reference describes the RESTful API you can use to interact with the HarmCheck platform. The REST API is usable via HTTP in any environment that supports HTTP requests.  

 

Authentication 

The HarmCheck API uses API keys for authentication. Create, manage, and learn more about API keys by contacting the HarmCheck team 

 

Remember that your API key is a secret! Do not share it with others or expose it in any client-side code (browsers, apps). API keys should be securely loaded from an environment variable or key management service on the server. 

 

API keys should be provided via HTTP Bearer authentication. 

 

Authorization: Bearer OPENAI_API_KEY 

 

Usage from these API requests counts as usage for the specified organization and project.  

 

 

 

End Points - POST /api/v1/reflections 

Description  

 

Submit a sentence or a list of sentences and receive classifier-based reflections for each one. This endpoint supports batch processing of input text and returns classifier responses including sentiment, threat detection, profanity analysis, and named entity recognition. 

 

HTTP Request 

 

POST https://reflect-web-prod-ejhmhadydbdsawbw.eastus2-01.azurewebsites.net/api/v1/reflections 

 

Headers 

Required

Yes

Yes (if auth enforced)

Description

Application/json

Bearer token for authenticated access

Header

Content-Type​

Authorization

Request Body 

 

  "sentence": "I think he's too old for the job" 

 

Description

A sentence to be analyzed

Type

 

string[] ​

Field

Sentence

Response 

  "label": "ds_ageist", 

  "labelType": "unlawful", 

  "prompt": "Age discrimination?", 

  "sentence": "I think he's too old for the job", 

  "dismissed": false 

 

 

Success Response 

200 OK – Returns the classifier results for each input sentence. 

 

Error Responses 

Description

Invalid request payload 

 

Unauthorized access 

 

Internal server error 

Status code

400

401

500

Request Body 

 

  "sentences": [ 

    "I think he's too old for the job", 

    "Stop being such a fucktard" 

  ] 

 

Response 

 

  { 

    "label": "ds_ageist", 

    "labelType": "unlawful", 

    "prompt": "Age discrimination?", 

    "sentence": "I think he's too old for the job", 

    "dismissed": false 

  }, 

  { 

    "label\"": "profane", 

    "labelType\"": "harmful", 

    "prompt\"": "Profane", 

    "sentence\"": "Stop being such a fucktard", 

    "dismissed\"": false 

  } 

 

 

 

Backward compatibility 

HarmCheck is committed to providing stability to API users by avoiding breaking changes in major API versions whenever reasonably possible.  

Introduction
Authentication
End Points - POST /api/v1/reflections 
Backward compatibility
Headers
Error responses
Success response
bottom of page