ready, you send prediction requests to the predict endpoint. The request shape is uniform across models; the payload inside each request follows the input schema documented on each model’s page.
Predict
Request shape
The request body is model-specific. See the per-model pages for input fields: All models accept an optionalrequest_id string that is echoed back in the response for tracing.
Response shape
Every response includes at minimum a top-level result object plus timing metadata:string
Echo of the client-supplied
request_id, or a server-assigned one when not provided.number
Wall-clock time to produce the prediction, from receipt to response.
object
Model-specific result. See each model’s page for its response fields.
Async predictions
For long-running jobs (for example, CryoNet reconstructions), passmode: "async" to receive a job ID immediately and poll for completion:
Request
Response
poll_url until status is completed, then read the result field.
Batching
Send an array of items in abatch field to run multiple predictions in a single request. Batches share GPU memory and are typically faster than sequential calls.
batch array in the same order as the request.