DecartProvider

Provider interface for creating Decart image and video models

Interface

interface DecartProvider extends ProviderV2 {
  image(modelId: DecartImageModelId): ImageModelV2;
  imageModel(modelId: DecartImageModelId): ImageModelV2;
  video(modelId: DecartVideoModelId): Experimental_VideoModelV3;
  videoModel(modelId: DecartVideoModelId): Experimental_VideoModelV3;
}

The DecartProvider interface extends the AI SDK’s ProviderV2 and provides methods to instantiate image and video generation models.

Methods

image()

image(modelId: DecartImageModelId): ImageModelV2

Creates an image generation model instance.

modelId · DecartImageModelId · required

The identifier of the image model to use.

See Image Models for available model IDs.

return · ImageModelV2

An image model instance compatible with AI SDK’s generateImage() function.

imageModel()

imageModel(modelId: DecartImageModelId): ImageModelV2

Alias for image(). Creates an image generation model instance.

modelId · DecartImageModelId · required

The identifier of the image model to use.

return · ImageModelV2

An image model instance compatible with AI SDK’s generateImage() function.

video()

video(modelId: DecartVideoModelId): Experimental_VideoModelV3

Creates a video generation model instance.

modelId · DecartVideoModelId · required

The identifier of the video model to use.

See Video Models for available model IDs.

return · Experimental_VideoModelV3

A video model instance compatible with AI SDK’s experimental_generateVideo() function.

videoModel()

videoModel(modelId: DecartVideoModelId): Experimental_VideoModelV3

Alias for video(). Creates a video generation model instance.

modelId · DecartVideoModelId · required

The identifier of the video model to use.

return · Experimental_VideoModelV3

A video model instance compatible with AI SDK’s experimental_generateVideo() function.

Examples

Creating an Image Model

import { createDecart } from '@decartai/ai-sdk-provider';
import { generateImage } from 'ai';

const decart = createDecart();

const { image } = await generateImage({
  model: decart.image('lucy-pro-t2i'),
  prompt: 'A serene mountain landscape'
});

Creating a Video Model

import { createDecart } from '@decartai/ai-sdk-provider';
import { experimental_generateVideo } from 'ai';

const decart = createDecart();

const { video } = await experimental_generateVideo({
  model: decart.video('lucy-pro-t2v'),
  prompt: 'Waves crashing on a beach at sunset'
});

Using Both Methods

import { createDecart } from '@decartai/ai-sdk-provider';

const decart = createDecart();

// These are equivalent
const imageModel1 = decart.image('lucy-pro-t2i');
const imageModel2 = decart.imageModel('lucy-pro-t2i');

// These are equivalent
const videoModel1 = decart.video('lucy-pro-t2v');
const videoModel2 = decart.videoModel('lucy-pro-t2v');

Unsupported Methods

The Decart provider does not support language or text embedding models. Calling these methods will throw a NoSuchModelError:

• languageModel(modelId: string) - Not supported
• textEmbeddingModel(modelId: string) - Not supported