Everywhere Inference Apps

Preview inference application deployment price

Changed on

Preview billing price for an entire ML application deployment. This endpoint calculates the total cost for all components across all regions, providing a comprehensive pricing estimate for the complete application.

post/cloud/v2/pricing/inference/applications

Request

  • Base URL
    https://api.gcore.com
  • URL
    https://api.gcore.com/cloud/v2/pricing/inference/applications
  • Auth
    HTTP apikey

Request body

componentsobject required

Dictionary of components configuration for pricing calculation.

regionsinteger[] required

List of region IDs where the application will be deployed

Example request

{
  "regions": [
    1,
    2,
    7
  ]
}

Response

OK

currency_code'AZN' | 'EUR' | 'USD' nullable required

Currency code (3 letter code per ISO 4217)

discount_percentnumber nullable required

Actual discount relative value

price_per_hournumber nullable required

Price of the item charged per hour

price_per_monthnumber nullable required

Price of the item charged per month

price_status'error' | 'hide' | 'show' required
price_without_discount_per_monthnumber nullable required

Total price VAT inclusive per month without discount

tax_percentnumber required

Tax rate applied to the subtotal, represented as a percentage

Example response

{
  "currency_code": "USD",
  "discount_percent": 0.16,
  "price_per_hour": 1,
  "price_per_month": 720,
  "price_status": "show",
  "price_without_discount_per_month": 604.8,
  "tax_percent": 17
}

Changes

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status

    • info

      added the non-success response with the status