Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.verlon.ai/llms.txt

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

The Verlon SDK provides a unified interface for AI capabilities across multiple providers. Use one SDK to access chat, image generation, embeddings, text-to-speech, video generation, and OCR.

​
Installation

npm install @verlon-ai/sdk

​
Quick Start

import { Verlon } from '@verlon-ai/sdk';

const verlon = new Verlon({
  apiKey: process.env.VERLON_API_KEY
});

const response = await verlon.chat({
  gateId: 'your-gate-id',
  data: {
    messages: [
      { role: 'user', content: 'Hello!' }
    ]
  }
});

console.log(response.content);

​
Configuration

​
Initialize the Client

import { Verlon } from '@verlon-ai/sdk';

const verlon = new Verlon({
  apiKey: 'your-api-key',        // Required
  baseUrl: 'https://custom.api'  // Optional, defaults to https://api.verlon.ai
});
Never commit API keys to version control. Use environment variables.

​
Get Your API Key

  1. Sign up at verlon.ai/signup
  2. Get your API key from the Dashboard
  3. Store it in an environment variable
.env
VERLON_API_KEY=your-api-key-here

​
Available Methods

The SDK provides methods for different AI capabilities:

Chat

Text generation with streaming, vision, and function calling

Images

Generate images from text prompts

Video

Create videos from text descriptions

Embeddings

Generate vector embeddings for text

Audio

Convert text to speech

OCR

Extract text from images

​
Response Structure

All SDK methods return a VerlonResponse object: 
interface VerlonResponse {
  // Common fields
  id: string;              // Request ID
  model: string;           // Model used
  cost: number;            // Request cost in USD
  latency: number;         // Response time in ms

  // Method-specific fields
  content?: string;        // Chat response text
  data?: any[];            // Image/video/embedding data
  url?: string;            // Audio file URL
  text?: string;           // OCR extracted text

  // Usage statistics
  usage?: {
    promptTokens: number;
    completionTokens: number;
    totalTokens: number;
  };
}

​
Error Handling

Wrap SDK calls in try-catch blocks: 
try {
  const response = await verlon.chat({
    gateId: 'your-gate-id',
    data: {
      messages: [{ role: 'user', content: 'Hello!' }]
    }
  });

  console.log(response.content);
} catch (error) {
  console.error('Error:', error.message);
}

​
Common Error Messages

ErrorCause
Invalid tokenCheck your API key
Gate not foundVerify gate ID is correct
Rate limit exceededToo many requests, slow down
Insufficient creditsAdd credits to your account

​
TypeScript Support

The SDK is fully typed: 
import { Verlon, ChatRequest, VerlonResponse } from '@verlon-ai/sdk';

const verlon = new Verlon({
  apiKey: process.env.VERLON_API_KEY!
});

// TypeScript knows the structure
const response: VerlonResponse = await verlon.chat({
  gateId: 'your-gate-id',
  data: {
    messages: [
      { role: 'user', content: 'Hello!' }
    ]
  }
});

// Autocomplete and type safety
console.log(response.content);  // TypeScript knows this exists
console.log(response.cost);     // TypeScript knows this is a number

​
Environment Variables

Best practice for managing credentials: 
// Good ✅
const verlon = new Verlon({
  apiKey: process.env.VERLON_API_KEY
});

// Bad ❌
const verlon = new Verlon({
  apiKey: 'lyr_hardcoded_key'  // Never do this!
});

​
Next Steps

Explore specific capabilities:

Chat

Images

Video

Embeddings

Audio

OCR

Or learn about core concepts:

Gates & Routing

How Verlon routes requests to models

Creating Gates

Configure gates in the dashboard