Sign in

Systemone

Answer one or more questions about the content supplied in state.

You can mix question types in one request. Answers use the same names as the questions, so you can match each result to its question. The response also includes the model used and token usage.

post/v1/systemone

Request

  • Base URL: https://api.typesafe.ai (the document declares no server; this is the origin it was published from)
  • URL: https://api.typesafe.ai/v1/systemone
  • Auth: HTTP bearer

Request body

modelstring required

Name or alias of the model to use. Available names are returned by GET /v1/models.

questionsobject required

Questions to ask about the content, each with a name you choose. The response uses those names to identify the answers.

Example request

{
  "model": "jev-latest",
  "questions": {
    "billing": {
      "instructions": "Is this message about billing?",
      "type": "noul"
    }
  }
}

Response

Successful Response

modelstring required

Name of the model that answered the questions. May differ from the alias supplied in the request.

answersobject required

Answers keyed by the question names supplied in the request. Each answer's type matches its question's type.

Example response

{
  "model": "jev-latest",
  "answers": {
    "billing": {
      "noul": 0.98,
      "type": "noul"
    }
  },
  "usage": {
    "input_tokens": 120,
    "output_tokens": 12
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.