Chat Messages

Process a chat messages request.

POST /api/ai/v1/messages/chat

Chat Messages

cURL

curl --request POST \
  --url https://{subdomain}.domo.com/api/ai/v1/messages/chat \
  --header 'Content-Type: application/json' \
  --header 'X-DOMO-Developer-Token: <api-key>' \
  --data '
{
  "input": [
    {
      "role": "USER",
      "content": [
        {
          "type": "TEXT",
          "text": "Why is the sky blue?"
        }
      ]
    }
  ]
}
'

200

{
  "content": [
    {
      "type": "TEXT",
      "text": "The sky appears blue due to a phenomenon called Rayleigh scattering."
    }
  ],
  "modelId": "domo.domo_ai.domogpt-medium-v1.2:anthropic",
  "isCustomerModel": false,
  "sessionId": "e1f6a485-7fb6-4f71-b41c-37d6cb5f6bd3",
  "requestId": "df2256fd-d133-4ea1-b958-295be09be7c1",
  "stopReason": "END_TURN"
}

Authorizations

X-DOMO-Developer-Token · string · header · required

Body

application/json

Request for interacting with the chat message AI service.

input · object[]

The list of input messages to be processed by the AI.

Show child attributes

sessionId · string<uuid>

The unique identifier for the AI session associated with this request.

system · object[]

System-level messages or configurations to guide the AI's response.

Show child attributes

model · string

The identifier of the AI model to be used for generating a response.

modelConfiguration · object

Specific parameters or settings that configure the AI model behavior.

Show child attributes

temperature · number<double>

A parameter for controlling the randomness of the model's output.

maxTokens · integer<int32>

The maximum number of tokens to generate in the response.

responseFormat · object

Model response format specification for structured outputs.

Show child attributes

reasoningConfig · object

Configuration for reasoning behavior and effort level.

Show child attributes

Response

200

application/json

Successful chat messages response.

Response from a Messages API.

content · object[]

The list of content generated by the model.

Text-based message content.

Option 1

Option 2

Option 3

Option 4

Option 5

Show child attributes

modelId · string

The id of the model used to generate the response.

sessionId · string<uuid>

The id of the AI Session associated with this request.

stopReason · enum<string>

The reason that the model stopped.

Available options: TOOL_USE, MAX_TOKENS, STOP_SEQUENCE, END_TURN, CONTENT_FILTERED, SAFETY, UNKNOWN

modelProviderUsage · object

The token usage from the model provider.

Show child attributes