Skip to main content
Get started with Eden AI’s Universal AI endpoint for expert models (OCR, image analysis, text processing, and more).
You need credits to make API calls. For testing without using credits, use a sandbox token.

​
Prerequisites

  1. API Token - Get your token from the Eden AI dashboard
  2. Credits - Ensure your account has sufficient credits

​
Make Your First Call

The Universal AI endpoint handles all non-LLM features (OCR, image analysis, text processing, etc.) through a single endpoint. 
import requests

url = "https://api.edenai.run/v3/universal-ai"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

payload = {
    "model": "text/moderation/google",
    "input": {
        "text": "This is a sample text to moderate for harmful content."
    }
}

response = requests.post(url, headers=headers, json=payload)
result = response.json()
print(result)

​
Response

{
  "status": "success",
  "cost": 0.0001,
  "provider": "google",
  "feature": "text",
  "subfeature": "moderation",
  "output": {
    "nsfw_likelihood": 1,
    "items": [
      {"label": "Toxic", "likelihood": 1, "likelihood_score": 0.0908}
    ],
    "nsfw_likelihood_score": 0.0908
  }
}

​
Model Format

Use the format feature/subfeature/provider[/model]: 
feature/subfeature/provider[/model]
Examples:
  • text/moderation/google - Content moderation
  • ocr/financial_parser/google - Invoice/receipt parsing
  • image/generation/openai/dall-e-3 - Image generation
  • image/object_detection/amazon - Object detection

​
Available Features

FeatureDescriptionExample Models
TextModeration, AI detection, NERtext/moderation/openai
OCRDocument parsing, text extractionocr/financial_parser/google
ImageGeneration, detection, analysisimage/generation/openai/dall-e-3
AudioSpeech-to-text, text-to-speechaudio/tts/google
TranslationDocument translationtranslation/document/google

List all available models

Discover all expert models available through Eden AI.

​
Next Steps

Audio Features

Speech-to-text transcription and text-to-speech synthesis

OCR Features

Document parsing and text extraction

Image Features

Image generation and analysis

List All Models

Browse all expert model features