---
title: "AiCon V3 Alpha"
method: POST
path: "/api/ai/content/v3/alpha"
tags: ["AI Services"]
---

# AiCon V3 Alpha

`POST /api/ai/content/v3/alpha`

AiCon V3 Alpha is an online LLM designed specifically for Business Content Generation. It leverages live access to online data, ensuring the content it generates is not only highly creative and capable of complex situational thinking but also up-to-date. Trained on a foundation of actual business and financial data, with an emphasis on data security and privacy, AiCon V3 Alpha stands out as one of our most advanced models. Importantly, it provides citations for all sources referred to, enhancing transparency and reliability by linking back to the original data it has accessed.

## Request body

- object
  - `question` string — The Text or Command to be processed.
  - `preserve_history` boolean — Whether to preserve the conversation history of the user. If set to true, the conversation history will be preserved and the conversation history will be accepted as `conversation_history` in the request body.
  - `conversation_history` object[] — The conversation history of the user as an array of objects. Each object should have a `question` and `answer` property as the key and value respectively.
    - `conversation` string — The conversation between the user and the AI as a key value pair.
  - `randomness` integer — The randomness factor to be used while generating the content. The higher the randomness, the more creative the content will be. The value should be between 0 and 1. `0` means it will be absolutely to the point and stops hallucinations. `1` means it will be completely creative and creates a content surrounding your questions a lot.
  - `training_data` string — The training data to be used while generating the content. This can be used to pass in smaller content based on how you want the model to behave, and specific behavioural or restrictive traits you want to add. This is optional.
  - `stream_data` boolean — Whether to stream the data as it is being generated. If set to true, the response will be streamed as the data is being generated. This is useful when you want to generate a lot of content and want to save the data as it is being generated. You need to handle Server Sent Events for this use case.
  - `response_type` 'json' | 'text' — The type of output to be generated. You can choose between `json` and `text`. `json` will return the text detection results as a JSON object that is parseable. `text` will return the text results as a plain text string.

## Response `200`

Text Content Generated Successfully

- object
  - `status` string — Status indicating the success of the text moderation.
  - `content` string — The text content generated.
  - `processing_time` integer — The time taken to process the request, in milliseconds.
  - `processing_id` string — A universally unique identifier for the request. This can be used to track the request in the logs.
  - `processing_count` integer — The number of times the request has been processed. This is what is considered in the Billing Process. This is either the number of times the image is processed or the number of words that the server processes.
  - `sources` object[] — The sources that the AI referred to in order to generate the content, including citations.
    - `title` string — The title of the source.
    - `url` string — The URL of the source.
    - `description` string — A brief description of the source.
    - `favicon` string — The favicon URL of the source's website.

## Other responses

- `400` — Bad Request.
- `401` — Unauthorized
- `404` — Not Found
- `406` — Not Acceptable
- `500` — Internal Server Error

---

[API](https://skmtc.net/worqhat/apis/worqhat-ai-api-endpoints-2.md) · [All operations](https://skmtc.net/worqhat/apis/worqhat-ai-api-endpoints-2/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/worqhat/worqhat-ai-api-endpoints-2/versions/fc369f69a3e6/schema)