Submit a request
Every execution starts with aPOST to /v1/executions. You get a 202 Accepted response immediately — the actual AI processing happens asynchronously.
Response
id— use this to track the executionstatus— starts asPENDING, will move toPROCESSING→COMPLETEDorFAILEDhold_amount— the amount reserved from your balance (refunded if execution fails)expires_at— when the execution times out if no result is received
Using file references
If your model requires image or audio input, upload files first and reference them:ModelRoute never accepts raw URLs in execution input. All files must be uploaded first via the file upload flow, giving you a
file_ reference to use here. This ensures your files are never exposed to third-party providers.What happens next
After submitting, you have two options to get results:- Set up webhooks (recommended for production) — receive an
execution.completedevent automatically - Poll for status — check
GET /v1/executions/{id}until the status is terminal