Generate a chat completion

POST

/chat

Generate the next message in a chat with a provided model. This is a streaming endpoint, so there will be a series of responses. Streaming can be disabled using 'stream': false. The final response object will include statistics and additional data from the request.

Request

Body Params application/json

Examples

Responses

🟢200OK

application/json

A stream of JSON objects is returned

Body

🟠400Bad Request

🟠401Unauthorized

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://api.demandai.de/v1/chat' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gemma3:12b",
    "messages": [
        {
            "role": "user",
            "content": "why is the sky blue?"
        }
    ],
    "stream": true
}'

Response Example

200 - Example 1

{
    "model": "gemma3:12b",
    "created_at": "2025-08-03T13:55:26.107Z",
    "message": [
        {
            "role": "assistant",
            "content": "The"
        }
    ],
    "done": false
}

Modified at 2025-11-04 14:45:50

Generate a completion

Generate Embeddings