OpenAI-compatible chat completions | decision-machine-1 documentation

curl -X POST https://api.milliseconds.ai/v1/chat/completions \
     -H "Content-Type: application/json" \
     -d '{
  "model": "decision-machine-1",
  "messages": [
    {
      "role": "user",
      "content": "Book me a table for 4 at Nobu on Friday at 8pm"
    }
  ],
  "response_format": {
    "json_schema": {
      "name": "booking",
      "schema": {
        "properties": {
          "day": {
            "type": "string"
          },
          "party_size": {
            "type": "integer"
          },
          "restaurant": {
            "type": "string"
          },
          "time": {
            "type": "string"
          }
        },
        "type": "object"
      }
    },
    "type": "json_schema"
  }
}'

{
  "id": "chatcmpl-7f3a1c2e9b8d4e6f0a1b2c3d",
  "object": "chat.completion",
  "created": 1789000000,
  "model": "decision-machine-1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "{\"restaurant\":\"Nobu\",\"party_size\":4,\"day\":\"Friday\",\"time\":\"8pm\"}"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 16,
    "total_tokens": 28
  }
}

Drop-in for OpenAI clients with model: "decision-machine-1". Two modes: response_format: { type: "json_schema" } extracts the schema from the user messages and returns the JSON as the assistant content; tools picks a tool and fills its arguments (function calling). Plain chat is rejected with 400. stream: true returns one chunk then [DONE].

Drop-in for OpenAI clients with `model: "decision-machine-1"`. Two modes: `response_format: { type: "json_schema" }` extracts the schema from the user messages and returns the JSON as the assistant content; `tools` picks a tool and fills its arguments (function calling). Plain chat is rejected with 400. `stream: true` returns one chunk then [DONE].

Request

This endpoint expects an object.

modelstringRequired

messageslist of objectsRequired

response_formatobjectOptional

toolslist of objectsOptional

tool_choiceenum or objectOptional

streambooleanOptional

Response

Completion

idstring

object"chat.completion"

createdinteger-9007199254740991-9007199254740991

modelstring

choiceslist of objects

usageobject

Errors

400

Bad Request Error