POST
/
v1
/
chat
/
completions
curl --request POST \
  --url https://api.siliconstorm.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "DeepSeek-R1",
  "messages": [
    {
      "content": "Write a hello word and explain the code",
      "role": "user"
    }
  ],
  "stream": true
}'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "delta": {
        "role": "<string>",
        "content": "<string>"
      },
      "finish_reason": "<string>"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123
  }
}

The REST API endpoint can be used with the locally running MindsDB at https://api.siliconstorm.ai/v1/chat/completions.

Authorizations

​
Authorization
string
header
required

Use the following format for authentication: Bearer <your api key>.

Body

application/json
Plant to add to the store
​
model
enum<string>
default:DeepSeek-R1
required

The model to use for processing

Available options:
DeepSeek-R1
​
messages
object[]
required

Array of messages

​
stream
boolean
required

Flag to indicate if the response should be streamed

Response

200 - application/json
Return example
​
id
string
required

Unique identifier for the completion chunk

​
object
string
required

The object type, always 'chat.completion.chunk'

​
created
integer
required

Timestamp of the creation

​
model
string
required

The model used for generating the response

​
choices
object[]
required

The choices array containing the chat response content

​
usage
object | null

Token usage details, included in the final response when completed