Shaping

Estimate FP4 preparation cost

Changed on

Reports the price and expected wall-clock time for preparing the model named by model_object_id or the deprecated adapter_object_id without creating a job. The request body is the same as POST /shaping/prepare-for-fp4-inference, so a caller can price exactly the job it is about to submit.

post/v1/shaping/prepare-for-fp4-inference/estimate

Request

  • Base URL
    https://api.together.ai
  • URL
    https://api.together.ai/v1/shaping/prepare-for-fp4-inference/estimate
  • Auth
    HTTP bearer

Request body

Example request

{
  "inputs": {
    "model_object_id": "ml_CeG3fF6pyEViU8dE8pk7R",
    "model_revision_id": "rv_CeG3faPBj2ABwbAaHPTmx",
    "calibration_file_id": "file-5f1b0c7a-2d19-4a3e-9c60-8ab41c2f7d35"
  }
}

Response

Estimate for the described job.

price_usdnumber double required

Expected total run cost in US dollars.

time_hoursnumber double required

Expected wall-clock run time in hours, excluding queue time.

credit_limitnumber double required

Project credit limit in US dollars.

allowed_to_proceedboolean required

Whether a create request at this price would be accepted.

Example response

{
  "price_usd": 28.76,
  "time_hours": 4,
  "credit_limit": 500,
  "allowed_to_proceed": true
}

Changes