Serverless AI Text Conversation

AI powered conversational service that generates responses to user messages, supporting conversation history and context.

Endpoint

Generate conversational AI responses with context and history

POSThttps://api.xtartapp.com/text/conversation

You must use a Bearer token provided by the dashboard to use for authentication. Add the token to the Authorization header.

Name	Type	Required	Max	Description
ask	string	Yes	1000	The user input message.
behavior	string	No	-	Custom behavior instruction for the assistant (defaults to 'You are a helpful AI assistant.')
history	array of objects	No	25	Previous conversation history between user and assistant.
history[].role	string	Yes	-	The role of the message sender (user or assistant)
history[].content	string	Yes	500	The message content.
context	string	No	25000	Optional context information that helps the assistant generate better responses (max 25 000 characters).
language	string	No	-	The language code for the assistant response.

Name	Type	Description
data	object	The assistant response data.
data.response	string	The assistant response text.
metadata	object	Metadata about the execution process.
metadata.cost	number	The cost of the execution request.

{
   "error": "string", 
   "code": "string"
}

HTTP Status	Error Code	Message
400	INVALID_PAYLOAD	Occurs when the payload is invalid.
400	INVALID_REQUEST	The request is invalid.
400	TEXT_CONVERSATION_ERROR	Could not generate response \| parsing error.
400	HARM_CONTENT	The content is harmful and cannot be processed.
400	INSUFFICIENT_BALANCE	The user has insufficient balance.
400	INPUT_TOO_LONG	The input text exceeds the maximum length.
401	UNAUTHORIZED	The token is invalid.
429	TOO_MANY_REQUESTS	The request limit has been reached.