Run a task with the specified inputs and receive structured output.
This endpoint executes the task using its active revision(s) and returns the results. Key features:
Required:
Optional:
The response includes:
The unique identifier of the organization.
The unique identifier of the project.
The specific Task to reference.
Optional Task Revision ID to use for execution. If not provided, an active revision will be selected based on traffic weights.
The input data for the Task in JSON format. Must include values for all dynamic parameters referenced in the Task’s user_prompt.
Example: {"text": "analyze this content", "max_length": 100}
Not required if image_required=true
and there are no dynamic parameters in the prompt.
Successful Response
The unique identifier of the Task associated with this run.
The unique identifier of the Task Revision associated with this run.
The structured response from the Task execution.
Additional data about the Task execution, including submitted inputs and processed files.
The unique identifier of the Task Run.
The timestamp when the Task Run was created.
The number of tokens submit as input to the model.
The number of tokens generated and output by the model.
The total token usage for the TaskRun.
The execution time for the TaskRun in seconds.
The execution time for the TaskRun in seconds.