Run

Start a prediction, wait for completion, and download results

This is CLI workflow behavior, not a standalone REST endpoint. It composes generated API commands from this resource to submit work, wait for completion, and persist local results.

boltz-api predictions:structure-and-binding run

Options

Option	Description
--input [ --input ]	Structure and binding prediction input. Pass inline JSON/YAML, or use @json://... / @yaml://... for larger payload files. Include entities plus optional constraints, bonds, templates, binding settings, sample count, and model options. Keep --model, --idempotency-key, and --workspace-id as top-level flags.
--model string	Model to use for prediction
--idempotency-key string	Client-provided key to prevent duplicate submissions on retries
--workspace-id string	Target workspace ID (admin keys only; ignored for workspace keys)
--name string	Local run directory name under --root-dir
--run-dir string	Explicit local run directory path
--root-dir string	Root directory for generated local run directories (default: "boltz-experiments")
--poll-interval-seconds float	Polling interval while waiting for remote results (default: 5)
--progress-format jsonl	Format for progress logs written to stderr (jsonl or text). jsonl is the default agent-friendly format. (default: "jsonl")
--verbose, -v	Print text progress logs to stderr when --progress-format text is selected (default: false)
--help, -h	show help