Answers and responses

Response

typesafe_sdk.SystemOneResponse

pydantic-model Bases: Response Answers grouped by question type with model and usage metadata. See System One for details.

Show JSON schema:

Details

{
  "$defs": {
    "BoxAnswer": {
      "description": "A located box with its confidence.",
      "properties": {
        "type": {
          "const": "box",
          "default": "box",
          "title": "Type",
          "type": "string"
        },
        "box": {
          "$ref": "#/$defs/BoxCoordinates"
        },
        "confidence": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "title": "Confidence"
        }
      },
      "required": [
        "box",
        "confidence"
      ],
      "title": "BoxAnswer",
      "type": "object"
    },
    "BoxCoordinates": {
      "description": "A box's edges as fractions of the image's height (`top`, `bottom`) and width (`left`, `right`).",
      "properties": {
        "top": {
          "description": "Top edge of the box, as a fraction of image height from the top (0-1).",
          "examples": [
            0.2
          ],
          "title": "Top",
          "type": "number"
        },
        "bottom": {
          "description": "Bottom edge of the box, as a fraction of image height from the top (0-1).",
          "examples": [
            0.66
          ],
          "title": "Bottom",
          "type": "number"
        },
        "left": {
          "description": "Left edge of the box, as a fraction of image width from the left (0-1).",
          "examples": [
            0.19
          ],
          "title": "Left",
          "type": "number"
        },
        "right": {
          "description": "Right edge of the box, as a fraction of image width from the left (0-1).",
          "examples": [
            0.68
          ],
          "title": "Right",
          "type": "number"
        }
      },
      "required": [
        "top",
        "bottom",
        "left",
        "right"
      ],
      "title": "BoxCoordinates",
      "type": "object"
    },
    "ChoiceAnswer": {
      "description": "A selected label and its probabilities.\n\nSee the [choice primitive](https://docs.typesafe.ai/go/choice) for details.",
      "properties": {
        "type": {
          "const": "choice",
          "default": "choice",
          "title": "Type",
          "type": "string"
        },
        "choice": {
          "description": "The name of the choice with the highest probability among the question's criteria.",
          "examples": [
            "angry"
          ],
          "title": "Choice",
          "type": "string"
        },
        "confidence": {
          "description": "Confidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.",
          "examples": [
            0.9
          ],
          "title": "Confidence",
          "type": "number"
        },
        "probabilities": {
          "additionalProperties": {
            "type": "number"
          },
          "description": "Probability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.",
          "examples": [
            {
              "angry": 0.8,
              "calm": 0.1,
              "excited": 0.1
            }
          ],
          "title": "Probabilities",
          "type": "object"
        }
      },
      "required": [
        "choice",
        "confidence",
        "probabilities"
      ],
      "title": "ChoiceAnswer",
      "type": "object"
    },
    "NoulAnswer": {
      "description": "A yes/no answer.\n\nSee the [noul primitive](https://docs.typesafe.ai/go/noul) for details.",
      "properties": {
        "type": {
          "const": "noul",
          "default": "noul",
          "title": "Type",
          "type": "string"
        },
        "noul": {
          "description": "Probability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.",
          "examples": [
            0.98
          ],
          "title": "Noul",
          "type": "number"
        }
      },
      "required": [
        "noul"
      ],
      "title": "NoulAnswer",
      "type": "object"
    },
    "ScoreAnswer": {
      "description": "An expected score with its rubric and probabilities.\n\nSee the [score primitive](https://docs.typesafe.ai/go/score) for details.",
      "properties": {
        "type": {
          "const": "score",
          "default": "score",
          "title": "Type",
          "type": "string"
        },
        "score": {
          "description": "Expected score: the probability-weighted average of the rubric levels. May fall between integer levels.",
          "examples": [
            1.7
          ],
          "title": "Score",
          "type": "number"
        },
        "confidence": {
          "description": "Confidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.",
          "examples": [
            0.9
          ],
          "title": "Confidence",
          "type": "number"
        },
        "legend": {
          "additionalProperties": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "items": {},
                "type": "array"
              }
            ]
          },
          "title": "Legend",
          "type": "object"
        },
        "probabilities": {
          "additionalProperties": {
            "type": "number"
          },
          "title": "Probabilities",
          "type": "object"
        }
      },
      "required": [
        "score",
        "confidence",
        "legend",
        "probabilities"
      ],
      "title": "ScoreAnswer",
      "type": "object"
    },
    "Usage": {
      "description": "Token counts for a request, when reported by the API.",
      "properties": {
        "input_tokens": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Input Tokens"
        },
        "output_tokens": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Output Tokens"
        }
      },
      "title": "Usage",
      "type": "object"
    }
  },
  "description": "Answers grouped by question type with model and usage metadata.\n\nSee [System One](https://docs.typesafe.ai/go/system-one) for details.",
  "properties": {
    "model": {
      "title": "Model",
      "type": "string"
    },
    "usage": {
      "$ref": "#/$defs/Usage"
    },
    "answers": {
      "additionalProperties": {
        "discriminator": {
          "mapping": {
            "box": "#/$defs/BoxAnswer",
            "choice": "#/$defs/ChoiceAnswer",
            "noul": "#/$defs/NoulAnswer",
            "score": "#/$defs/ScoreAnswer"
          },
          "propertyName": "type"
        },
        "oneOf": [
          {
            "$ref": "#/$defs/NoulAnswer"
          },
          {
            "$ref": "#/$defs/ChoiceAnswer"
          },
          {
            "$ref": "#/$defs/ScoreAnswer"
          },
          {
            "$ref": "#/$defs/BoxAnswer"
          }
        ]
      },
      "title": "Answers",
      "type": "object"
    }
  },
  "required": [
    "model",
    "usage"
  ],
  "title": "SystemOneResponse",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

model (str)
usage (Usage)
answers (dict[str, Answer])

request_id

cached property The x-typesafe-request-id response header.

raw_http_response

property

raw_http_response: httpx2.Response

The underlying httpx2.Response, exposing status, headers, and body.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

model

pydantic-field The model used to answer the request.

usage

pydantic-field Token usage for the request.

answers

pydantic-field All answer objects keyed by question name.

nouls

cached property Yes/no answers keyed by question name.

choices

cached property Choice answers keyed by question name.

scores

cached property Score answers keyed by question name.

boxes

cached property Box answers keyed by question name.

typesafe_sdk.Usage

pydantic-model Bases: wire.Usage Token counts for a request, when reported by the API.

Show JSON schema:

Details

{
  "description": "Token counts for a request, when reported by the API.",
  "properties": {
    "input_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Input Tokens"
    },
    "output_tokens": {
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Output Tokens"
    }
  },
  "title": "Usage",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

input_tokens (int | None)
output_tokens (int | None)

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

input_tokens

pydantic-field Number of input tokens used, or None when the API did not report it.

output_tokens

pydantic-field Number of output tokens used, or None when the API did not report it.

Answers

typesafe_sdk.NoulAnswer

pydantic-model Bases: wire.NoulAnswer A yes/no answer. See the noul primitive for details.

Show JSON schema:

Details

{
  "description": "A yes/no answer.\n\nSee the [noul primitive](https://docs.typesafe.ai/go/noul) for details.",
  "properties": {
    "type": {
      "const": "noul",
      "default": "noul",
      "title": "Type",
      "type": "string"
    },
    "noul": {
      "description": "Probability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.",
      "examples": [
        0.98
      ],
      "title": "Noul",
      "type": "number"
    }
  },
  "required": [
    "noul"
  ],
  "title": "NoulAnswer",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

noul (float)
type (Literal[‘noul’])

noul

pydantic-field Probability of a yes answer or a true statement, from 0 to 1. Values near 1 favor yes or true, values near 0 favor no or false, and values near 0.5 indicate uncertainty.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

typesafe_sdk.ChoiceAnswer

pydantic-model Bases: wire.ChoiceAnswer A selected label and its probabilities. See the choice primitive for details.

Show JSON schema:

Details

{
  "description": "A selected label and its probabilities.\n\nSee the [choice primitive](https://docs.typesafe.ai/go/choice) for details.",
  "properties": {
    "type": {
      "const": "choice",
      "default": "choice",
      "title": "Type",
      "type": "string"
    },
    "choice": {
      "description": "The name of the choice with the highest probability among the question's criteria.",
      "examples": [
        "angry"
      ],
      "title": "Choice",
      "type": "string"
    },
    "confidence": {
      "description": "Confidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.",
      "examples": [
        0.9
      ],
      "title": "Confidence",
      "type": "number"
    },
    "probabilities": {
      "additionalProperties": {
        "type": "number"
      },
      "description": "Probability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.",
      "examples": [
        {
          "angry": 0.8,
          "calm": 0.1,
          "excited": 0.1
        }
      ],
      "title": "Probabilities",
      "type": "object"
    }
  },
  "required": [
    "choice",
    "confidence",
    "probabilities"
  ],
  "title": "ChoiceAnswer",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

choice (str)
confidence (float)
probabilities (dict[str, float])
type (Literal[‘choice’])

choice

pydantic-field The name of the choice with the highest probability among the question’s criteria.

confidence

pydantic-field Confidence in the selected choice, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain selections for review.

probabilities

pydantic-field Probability of each choice in criteria, keyed by choice name, from 0 to 1. Shows how likely the alternatives are; values sum to approximately 1.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

typesafe_sdk.ScoreAnswer

pydantic-model Bases: wire.ScoreAnswer An expected score with its rubric and probabilities. See the score primitive for details.

Show JSON schema:

Details

{
  "description": "An expected score with its rubric and probabilities.\n\nSee the [score primitive](https://docs.typesafe.ai/go/score) for details.",
  "properties": {
    "type": {
      "const": "score",
      "default": "score",
      "title": "Type",
      "type": "string"
    },
    "score": {
      "description": "Expected score: the probability-weighted average of the rubric levels. May fall between integer levels.",
      "examples": [
        1.7
      ],
      "title": "Score",
      "type": "number"
    },
    "confidence": {
      "description": "Confidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.",
      "examples": [
        0.9
      ],
      "title": "Confidence",
      "type": "number"
    },
    "legend": {
      "additionalProperties": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "additionalProperties": true,
            "type": "object"
          },
          {
            "items": {},
            "type": "array"
          }
        ]
      },
      "title": "Legend",
      "type": "object"
    },
    "probabilities": {
      "additionalProperties": {
        "type": "number"
      },
      "title": "Probabilities",
      "type": "object"
    }
  },
  "required": [
    "score",
    "confidence",
    "legend",
    "probabilities"
  ],
  "title": "ScoreAnswer",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

score (float)
confidence (float)
type (Literal[‘score’])
legend (dict[int, str | dict[str, Any] | list[Any]])
probabilities (dict[int, float])

score

pydantic-field Expected score: the probability-weighted average of the rubric levels. May fall between integer levels.

confidence

pydantic-field Confidence in the score, from 0 to 1. Higher values indicate greater certainty; use lower values to flag uncertain ratings for review.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

legend

pydantic-field Rubric descriptions keyed by integer score.

probabilities

pydantic-field Probabilities keyed by integer score.

typesafe_sdk.BoxAnswer

pydantic-model Bases: wire.BoxAnswer A located box with its confidence.

Show JSON schema:

Details

{
  "$defs": {
    "BoxCoordinates": {
      "description": "A box's edges as fractions of the image's height (`top`, `bottom`) and width (`left`, `right`).",
      "properties": {
        "top": {
          "description": "Top edge of the box, as a fraction of image height from the top (0-1).",
          "examples": [
            0.2
          ],
          "title": "Top",
          "type": "number"
        },
        "bottom": {
          "description": "Bottom edge of the box, as a fraction of image height from the top (0-1).",
          "examples": [
            0.66
          ],
          "title": "Bottom",
          "type": "number"
        },
        "left": {
          "description": "Left edge of the box, as a fraction of image width from the left (0-1).",
          "examples": [
            0.19
          ],
          "title": "Left",
          "type": "number"
        },
        "right": {
          "description": "Right edge of the box, as a fraction of image width from the left (0-1).",
          "examples": [
            0.68
          ],
          "title": "Right",
          "type": "number"
        }
      },
      "required": [
        "top",
        "bottom",
        "left",
        "right"
      ],
      "title": "BoxCoordinates",
      "type": "object"
    }
  },
  "description": "A located box with its confidence.",
  "properties": {
    "type": {
      "const": "box",
      "default": "box",
      "title": "Type",
      "type": "string"
    },
    "box": {
      "$ref": "#/$defs/BoxCoordinates"
    },
    "confidence": {
      "anyOf": [
        {
          "type": "number"
        },
        {
          "type": "null"
        }
      ],
      "title": "Confidence"
    }
  },
  "required": [
    "box",
    "confidence"
  ],
  "title": "BoxAnswer",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

type (Literal[‘box’])
box (BoxCoordinates)
confidence (float | None)

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

box

pydantic-field The box’s edges as fractions of the image’s height and width, from 0 to 1.

confidence

pydantic-field Confidence for the box, from 0 to 1, or None when the model does not provide it.

typesafe_sdk.BoxCoordinates

pydantic-model Bases: wire.BoxCoordinates A box’s edges as fractions of the image’s height (top, bottom) and width (left, right).

Show JSON schema:

Details

{
  "description": "A box's edges as fractions of the image's height (`top`, `bottom`) and width (`left`, `right`).",
  "properties": {
    "top": {
      "description": "Top edge of the box, as a fraction of image height from the top (0-1).",
      "examples": [
        0.2
      ],
      "title": "Top",
      "type": "number"
    },
    "bottom": {
      "description": "Bottom edge of the box, as a fraction of image height from the top (0-1).",
      "examples": [
        0.66
      ],
      "title": "Bottom",
      "type": "number"
    },
    "left": {
      "description": "Left edge of the box, as a fraction of image width from the left (0-1).",
      "examples": [
        0.19
      ],
      "title": "Left",
      "type": "number"
    },
    "right": {
      "description": "Right edge of the box, as a fraction of image width from the left (0-1).",
      "examples": [
        0.68
      ],
      "title": "Right",
      "type": "number"
    }
  },
  "required": [
    "top",
    "bottom",
    "left",
    "right"
  ],
  "title": "BoxCoordinates",
  "type": "object"
}

Config:

extra: ignore
frozen: True
strict: True

Fields:

top (float)
bottom (float)
left (float)
right (float)

top

pydantic-field Top edge of the box, as a fraction of image height from the top (0-1).

bottom

pydantic-field Bottom edge of the box, as a fraction of image height from the top (0-1).

left

pydantic-field Left edge of the box, as a fraction of image width from the left (0-1).

right

pydantic-field Right edge of the box, as a fraction of image width from the left (0-1).

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

typesafe_sdk.Answer

module-attribute An answer to a single question, identified by its type.

Available models

typesafe_sdk.ListModelsResponse

pydantic-model Bases: Response The models available to the account.

Show JSON schema:

Details

{
  "$defs": {
    "ModelMetadata": {
      "description": "Metadata describing a single available model.",
      "properties": {
        "name": {
          "title": "Name",
          "type": "string"
        },
        "description": {
          "title": "Description",
          "type": "string"
        },
        "release_date": {
          "title": "Release Date",
          "type": "string"
        }
      },
      "required": [
        "name",
        "description",
        "release_date"
      ],
      "title": "ModelMetadata",
      "type": "object"
    }
  },
  "description": "The models available to the account.",
  "properties": {
    "models": {
      "items": {
        "$ref": "#/$defs/ModelMetadata"
      },
      "title": "Models",
      "type": "array"
    }
  },
  "required": [
    "models"
  ],
  "title": "ListModelsResponse",
  "type": "object"
}

Fields:

models (tuple[ModelMetadata, …])

request_id

cached property The x-typesafe-request-id response header.

raw_http_response

property

raw_http_response: httpx2.Response

The underlying httpx2.Response, exposing status, headers, and body.

model_config

class-attribute instance-attribute

model_config = ConfigDict(
    extra="ignore", frozen=True, strict=True
)

models

pydantic-field The available models.

typesafe_sdk.ModelMetadata

pydantic-model Bases: Schema Metadata describing a single available model.

Show JSON schema:

Details

{
  "description": "Metadata describing a single available model.",
  "properties": {
    "name": {
      "title": "Name",
      "type": "string"
    },
    "description": {
      "title": "Description",
      "type": "string"
    },
    "release_date": {
      "title": "Release Date",
      "type": "string"
    }
  },
  "required": [
    "name",
    "description",
    "release_date"
  ],
  "title": "ModelMetadata",
  "type": "object"
}

Fields:

name (str)
description (str)
release_date (str)

name

pydantic-field Model name or alias accepted by a request’s model field.

description

pydantic-field Human-readable description of the model and its capabilities.

release_date

pydantic-field Model release date, formatted as YYYY-MM-DD.

​Response

​typesafe_sdk.SystemOneResponse

​request_id

​raw_http_response

​model_config

​model

​usage

​answers

​nouls

​choices

​scores

​boxes

​typesafe_sdk.Usage

​model_config

​input_tokens

​output_tokens

​Answers

​typesafe_sdk.NoulAnswer

​noul

​model_config

​typesafe_sdk.ChoiceAnswer

​choice

​confidence

​probabilities

​model_config

​typesafe_sdk.ScoreAnswer

​score

​confidence

​model_config

​legend

​probabilities

​typesafe_sdk.BoxAnswer

​model_config

​box

​confidence

​typesafe_sdk.BoxCoordinates

​top

​bottom

​left

​right

​model_config

​typesafe_sdk.Answer

​Available models

​typesafe_sdk.ListModelsResponse

​request_id

​raw_http_response

​model_config

​models

​typesafe_sdk.ModelMetadata

​name

​description

​release_date

Response

typesafe_sdk.SystemOneResponse

request_id

raw_http_response

model_config

model

usage

answers

nouls

choices

scores

boxes

typesafe_sdk.Usage

model_config

input_tokens

output_tokens

Answers

typesafe_sdk.NoulAnswer

noul

model_config

typesafe_sdk.ChoiceAnswer

choice

confidence

probabilities

model_config

typesafe_sdk.ScoreAnswer

score

confidence

model_config

legend

probabilities

typesafe_sdk.BoxAnswer

model_config

box

confidence

typesafe_sdk.BoxCoordinates

top

bottom

left

right

model_config

typesafe_sdk.Answer

Available models

typesafe_sdk.ListModelsResponse

request_id

raw_http_response

model_config

models

typesafe_sdk.ModelMetadata

name

description

release_date