Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/DecartAI/ai-sdk-provider/llms.txt

Use this file to discover all available pages before exploring further.

The Decart provider can be configured with various options to customize its behavior. This guide covers all available configuration options for the createDecart() function.

​
Default Provider Instance

The simplest way to use the Decart provider is with the default instance: 
import { decart } from '@decartai/ai-sdk-provider';
This instance uses default settings and reads the API key from the DECART_API_KEY environment variable.

​
Custom Provider Configuration

For advanced use cases, you can create a custom provider instance with createDecart(): 
import { createDecart } from '@decartai/ai-sdk-provider';

const decart = createDecart({
  apiKey: 'your-api-key',
  baseURL: 'https://custom-proxy.example.com',
  headers: {
    'Custom-Header': 'value',
  },
  fetch: customFetchImplementation,
});

​
Configuration Options

All configuration options are optional and passed as properties of the settings object.

​
apiKey

​
apiKey
string
API key for authenticating with the Decart API. If not provided, the provider will attempt to read from the DECART_API_KEY environment variable.
Example: 
const decart = createDecart({
  apiKey: 'your-api-key',
});
The API key is sent using the X-API-KEY header in all requests.

​
baseURL

​
baseURL
string
default:"https://api.decart.ai"
Custom base URL for API requests. Useful for routing requests through a proxy server or using a different API endpoint.
Example: 
const decart = createDecart({
  baseURL: 'https://proxy.example.com',
});
Trailing slashes are automatically removed from the base URL.

​
headers

​
headers
Record<string, string>
Additional HTTP headers to include in all API requests. These headers are merged with the default headers.
Example: 
const decart = createDecart({
  headers: {
    'X-Custom-Header': 'custom-value',
    'X-Request-ID': 'unique-request-id',
  },
});
Custom headers will be merged with default headers. If you provide headers that conflict with default headers (like X-API-KEY), your custom values will take precedence.

​
fetch

​
fetch
FetchFunction
Custom fetch implementation to use for HTTP requests. This allows you to intercept requests, add middleware, or provide a custom fetch implementation for testing.
Type definition: 
type FetchFunction = (input: RequestInfo, init?: RequestInit) => Promise<Response>;
Example - Request Interceptor: 
const customFetch: FetchFunction = async (input, init) => {
  console.log('Making request to:', input);
  const response = await fetch(input, init);
  console.log('Response status:', response.status);
  return response;
};

const decart = createDecart({
  fetch: customFetch,
});
Example - Testing with Mock Fetch: 
import { createDecart } from '@decartai/ai-sdk-provider';

const mockFetch = async (input: RequestInfo, init?: RequestInit) => {
  // Return mock responses for testing
  return new Response(JSON.stringify({ job_id: 'test-123' }), {
    status: 200,
    headers: { 'Content-Type': 'application/json' },
  });
};

const decart = createDecart({
  fetch: mockFetch,
});

​
Complete Configuration Example

Here’s a complete example showing all configuration options together: 
import { createDecart } from '@decartai/ai-sdk-provider';
import type { FetchFunction } from '@ai-sdk/provider-utils';

const loggingFetch: FetchFunction = async (input, init) => {
  const start = Date.now();
  console.log(`[${new Date().toISOString()}] Request: ${input}`);
  
  const response = await fetch(input, init);
  const duration = Date.now() - start;
  
  console.log(`[${new Date().toISOString()}] Response: ${response.status} (${duration}ms)`);
  return response;
};

const decart = createDecart({
  apiKey: process.env.DECART_API_KEY,
  baseURL: 'https://api.decart.ai',
  headers: {
    'X-Application-Name': 'my-app',
    'X-Application-Version': '1.0.0',
  },
  fetch: loggingFetch,
});

// Use the configured provider
const { image } = await generateImage({
  model: decart.image('lucy-pro-t2i'),
  prompt: 'A beautiful sunset',
});

​
Environment Variables

The Decart provider automatically reads from environment variables:
VariableDescriptionDefault
DECART_API_KEYAPI key for authenticationRequired if apiKey option is not provided
Example .env file: 
DECART_API_KEY=your-api-key-here

​
User Agent

The provider automatically adds a User-Agent header to all requests with the format: 
ai-sdk/decart/{version}
This helps Decart track SDK usage and version information.

Build docs developers (and LLMs) love

Get started for freeTalk to us