Generate a chat completion

POST

https://api.genxt.ai/api/chat

This endpoint facilitates the generation of the next message in a conversation using a specified AI model. It supports maintaining a chat history to provide context to the model. The endpoint also supports streaming responses, which can be disabled to receive a single response object.

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.genxt.ai/api/chat' \
--header 'Content-Type: application/json' \
--data-raw ''

Response Example

{
  "model": "string",
  "created_at": "2019-08-24T14:15:22Z",
  "message": {
    "role": "string",
    "content": "string"
  },
  "done": true,
  "total_duration": 0
}

Request

Authorization

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

Body Params application/json

model

string

required

The name of the AI model to use for generating the chat completion.

messages

array [object {3}]

required

role

string

optional

The role of the message sender, such as user, system, or assistant.

content

string

optional

The content of the message.

images

array[string <base64>]

optional

Optional base64-encoded images for multimodal chat interactions.

stream

boolean

optional

If true, chat responses are streamed; if false, a single JSON response is provided.

Default:

true

Examples

Responses

🟢200Successfully generated the next message in the chat with model statistics and response data.

application/json

Body

model

string

optional

created_at

string <date-time>

optional

message

object

optional

role

string

optional

content

string

optional

done

boolean

optional

total_duration

integer <int64>

optional

Total time taken for generating the

Modified at 2024-11-25 19:58:30

Generate a completion

List Local Models