predictions module

Predictions module.

class ErrorSource(StrEnum)

Bases: StrEnum

Enumeration of possible error sources.

internal = 'internal'

external = 'external'

class Status(StrEnum)

Bases: StrEnum

Enumeration of possible prediction statuses.

pending = 'pending'

started = 'started'

failed = 'failed'

succeeded = 'succeeded'

class TaskError

Bases: TypedDict

Represents an error that occurred during a prediction.

source : ErrorSource

message : str

detail : list[JsonValue] | Mapping[str, JsonValue] | str | bool | int | float | None

class PredictionModel

Bases: TypedDict

Represents the prediction model.

owner : str

Username of the model’s owner.

name : str

Name of the model.

version_number : int

Version number of the model.

class Prediction

Bases: TypedDict

Represents a prediction.

url : str

URL to access the prediction resource.

id : str

Unique identifier for the prediction.

created_at : str

Timestamp when the prediction was created.

status : Status

Current status of the prediction.

updated_at : str

Timestamp of the last update to the prediction.

setup_time : str | None

Time taken to set up the prediction environment.

execution_time : str | None

Time taken to execute the prediction.

model : PredictionModel

The model of the prediction.

class PredictionWithIO

Bases: Prediction

Represents a prediction with I/O details.

input : list[JsonValue] | Mapping[str, JsonValue] | str | bool | int | float | None

Input data provided for the prediction.

output : list[JsonValue] | Mapping[str, JsonValue] | str | bool | int | float | None

Output generated by the prediction.

logs : list[str] | None

Logs generated during prediction execution.

setup_logs : list[str] | None

Logs generated during setup.

error : TaskError | None

Error details if the prediction failed.

url : str

id : str

created_at : str

status : Status

updated_at : str

setup_time : str | None

execution_time : str | None

model : PredictionModel

class Webhook

Bases: TypedDict

Represents webhook details.

url : str

HTTP URL to POST updates to.

secret : NotRequired[str | None]

Secret to generate the signature for the webhook.

class CreatePredictionParams

Bases: TypedDict

Prediction creation params.

input : list[JsonValue] | Mapping[str, JsonValue] | str | bool | int | float | None

Input data provided for the prediction.

webhook : NotRequired[Webhook | None]

Details about the webhook to post prediction updates to.

validate_input : NotRequired[bool]

Enable input validation against the schema before processing.

class WaitOptions(poll_interval=1.0, on_poll=None)

Bases: _BaseWaitOptions

Options for customizing wait behaviour.

• Parameters:
  • poll_interval (float)
  • on_poll (Callable [ [PredictionWithIO ] , None ] | None)

on_poll : Callable[[PredictionWithIO], None] | None = None

Optional callback that receives the latest prediction after each poll.

class AsyncWaitOptions(poll_interval=1.0, on_poll=None)

Bases: _BaseWaitOptions

Options for customizing asynchronous wait behaviour.

• Parameters:
  • poll_interval (float)
  • on_poll (Callable [ [PredictionWithIO ] , Awaitable *[*None ] ] | None)

on_poll : Callable[[PredictionWithIO], Awaitable[None]] | None = None

Optional callback that receives the latest prediction after each poll.

DEFAULT_WAIT_OPTIONS = WaitOptions(poll_interval=1.0, on_poll=None)

Default wait options.

DEFAULT_ASYNC_WAIT_OPTIONS = AsyncWaitOptions(poll_interval=1.0, on_poll=None)

Default async wait options.

class Predictions(api)

Bases: Resource

Initializes the Resource with an API instance.

• Parameters: api (API) – An instance of the API class.

get(prediction_id)

Get a prediction by id.

• Parameters: prediction_id (str) – The unique identifier of the prediction.
• Returns: The prediction object.
• Return type: PredictionWithIO

async async_get(prediction_id)

Get a prediction by id.

• Parameters: prediction_id (str) – The unique identifier of the prediction.
• Returns: The prediction object.
• Return type: PredictionWithIO

list(pagination_options=None)

List predictions.

• Parameters: pagination_options (Optional [PaginationOptions ]) – Optional settings to control pagination behavior.
• Returns: Paginated response containing predictions : and navigation metadata.
• Return type: PaginatedResponse[Prediction]

async async_list(pagination_options=None)

List predictions.

• Parameters: pagination_options (Optional [PaginationOptions ]) – Optional settings to control pagination behavior.
• Returns: Paginated response containing predictions : and navigation metadata.
• Return type: PaginatedResponse[Prediction]

create(params, model, wait=False, wait_options=WaitOptions(poll_interval=1.0, on_poll=None))

Create a prediction.

• Parameters:
  • model (str) – The model reference in either owner/name or owner/name:version-number format (for example: deepseek-ai/deepseek-r1 or deepseek-ai/deepseek-r1:1).
  • params (CreatePredictionParams) – Prediction creation params.
  • wait (bool) – If True, waits until the prediction reaches a terminal state. If False, returns the prediction immediately. Defaults to False.
  • wait_options (WaitOptions) – Options for customizing wait behavior. If not provided, default options are used.
• Returns: The new prediction.
• Return type: PredictionWithIO
• Raises: ValueError – When the provided model reference is not in owner/name or owner/name:version-number format.

async async_create(params, model, wait=False, wait_options=AsyncWaitOptions(poll_interval=1.0, on_poll=None))

Create a prediction.

• Parameters:
  • model (str) – The model reference in either owner/name or owner/name:version-number format (for example: deepseek-ai/deepseek-r1 or deepseek-ai/deepseek-r1:1).
  • params (CreatePredictionParams) – Prediction creation params.
  • wait (bool) – If True, waits until the prediction reaches a terminal state. If False, returns the prediction immediately. Defaults to False.
  • wait_options (AsyncWaitOptions) – Options for customizing wait behavior. If not provided, default options are used.
• Returns: The new prediction.
• Return type: PredictionWithIO
• Raises: ValueError – When the provided model reference is not in owner/name or owner/name:version-number format.

wait(predictionID, options=WaitOptions(poll_interval=1.0, on_poll=None))

Wait for a prediction to complete.

This method uses short polling to check the prediction status at regular intervals until it reaches a terminal state. It blocks execution and waits until the prediction has finished processing.

• Parameters:
  • predictionID (str) – Unique identifier of the prediction.
  • options (WaitOptions) – Options for customizing wait behavior. If not provided, default options are used.
• Returns: Prediction after completion.
• Return type: PredictionWithIO

async async_wait(predictionID, options=AsyncWaitOptions(poll_interval=1.0, on_poll=None))

Wait for a prediction to complete.

This method uses short polling to check the prediction status at regular intervals until it reaches a terminal state. It blocks execution and waits until the prediction has finished processing.

• Parameters:
  • predictionID (str) – Unique identifier of the prediction.
  • options (AsyncWaitOptions) – Options for customizing wait behavior. If not provided, default options are used.
• Returns: Prediction after completion.
• Return type: PredictionWithIO