Inference

Run inference on a trained model

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…

Run inference on a trained Fount model. Submit a dataset and a trained model name to generate forecasts and predictions. Use this endpoint after a training or tuning job has completed successfully.
Inference runs asynchronously and returns a job_name you can use to monitor progress and retrieve results via the task-status endpoint.

Authentication: Include your API key in the X-API-KEY request header.

Parameter descriptions:

ParameterDescription
model_nameThe name of the trained model to run inference with. Must match the model_name used in the training or tuning job.
datasetThe ID of the dataset to run inference on. This can be the same dataset used for training or a new dataset with the same column structure. Returned when you upload a file via the Upload endpoint.
batch_sizeNumber of rows to process per inference batch. Higher values may speed up inference on large datasets but require more memory. Must be greater than 0. Defaults to 8.

Body Params

Configuration for the inference process.

string
required

Path to the trained model checkpoint for inference.

string
required
integer
Defaults to 8

Batch size for inference.

Responses

Language
Credentials
Header
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json