Skip to main content
GET
Get Model Capabilities

Overview

This endpoint returns every video and image model available on the AI Studio endpoints together with the aspect ratios, durations, reference limits, audio support, and features each one accepts. It is generated from the same registry that validates generation requests, so it always matches what the API enforces. Use it to build model pickers or to validate requests before sending them, instead of hard-coding the tables from the documentation.
A valid API key is required to use this endpoint. Obtain your API key from the API Access page in your Pictory dashboard.

API Endpoint


Request Headers

string
required
API key for authentication (starts with pictai_)

Response

Success Response (200)

object
The model used when a request omits model: video for plain video generation, extend for a request with extendVideoUrl, and image for image generation.
array
The values accepted by the trainingPreset request field.
array
One entry per video model.
array
One entry per image model.
Retired models are handled in two ways:
  • Served by another model. The model stays in this list with retired: true and servedAs. pixverse5.5 in the example below is one. Your request is generated and billed by the servedAs model.
  • Refused. The model is left out of this list. Veo 3.1 Fast (veo3.1_fast) and Nova Canvas (nova-canvas) are refused.
A request for a refused model returns HTTP 400:
  • For Veo 3.1 Fast, the message is: “Veo Fast has been retired and is no longer available. Please choose a different model.” The closest model is veo3.1.
  • For Nova Canvas, the message is: “Nova Canvas has been retired and is no longer available. Please choose a different model.”
Credit rates are not part of this response. Refer to the pricing tables on the Generate Video and Generate Image pages.

Response Examples


Status Codes


Code Examples