runs

Re-enter a run at a step

Priced as a fraction of the tier: 25% from step 12 on, 50% for steps 8–11, 100% below that. With rerun_reason: "platform" the rerun is free, and is accepted only for a source run that failed on our side (409 rerun_not_platform otherwise).

post/v1/runs/{id}/rerun-from

Request

  • Base URL: https://api.hyperresearch.ai
  • URL: https://api.hyperresearch.ai/v1/runs/{id}/rerun-from
  • Auth: one of:
    • HTTP bearer
    • API key in cookie hr_session

Path parameters

idstring required

Request body

stepstring required
rerun_reason'platform'

Re-enter a run that failed on OUR side at no charge. Accepted only when the source run is failed with a platform failure (interrupted by a platform fault or restart, a platform limit, a stopped worker, exhausted automatic recovery, or an unavailable workspace store); any other source answers 409 rerun_not_platform. Omit it for the usual 25–100% rerun price.

Example request

{
  "levers": {
    "purpose": "decide",
    "report_language": "zh",
    "reader_expertise": "expert"
  }
}

Response

Rerun queued

idstring required
status'queued' required
tierstring required
price_centsinteger required
price_percent_of_tierinteger required
source_runstring required
resume_fromstring required
events_urlstring required
created_atstring required
rerun_reason'platform'

Present only on a zero-price rerun of a run that failed on our side; price_cents is then 0.

Changes

No recorded changes to this operation across all 1 revision of this API.