Eden AI V3 API Documentation

Welcome to the Eden AI V3 API - our next-generation unified API with OpenAI-compatible endpoints and a revolutionary single-endpoint architecture.

What’s New in V3?

Eden AI V3 introduces a completely redesigned API architecture that simplifies AI integration while maintaining full compatibility with OpenAI’s API format.

Key Innovations

Universal AI Endpoint - Access all AI features through a single endpoint with a unified request format. OpenAI-Compatible LLM - Drop-in replacement for OpenAI’s chat completions API with multi-provider support. Persistent File Storage - Upload files once, reference them in multiple requests with automatic expiration. Built-in API Discovery - Explore available features, providers, and schemas programmatically. Mandatory Streaming - All LLM responses use Server-Sent Events (SSE) for real-time output.

If you were a user before 2026/01/05, you still have access to the previous version: https://old-app.edenai.run/. We’ll continue supporting the old version until the end of 2026. If you’re looking for the documentation, you can find it here

Core Endpoints

1. Universal AI - Single Endpoint for Everything

Access all non-LLM features through one unified endpoint:

POST /v3/universal-ai

One endpoint for:

Text analysis (moderation, embeddings, AI detection)
OCR (text extraction, invoice/ID parsing)
Image processing (generation, detection, analysis)
Translation (document translation)

Example Request:

import requests

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

payload = {
    "model": "text/ai_detection/openai/gpt-4",
    "input": {
        "text": "This is a sample text to analyze"
    }
}

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

2. OpenAI-Compatible LLM

OpenAI-compatible chat completions with streaming:

POST /v3/llm/chat/completions

Drop-in replacement for OpenAI API:

import requests

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

payload = {
    "model": "openai/gpt-4",
    "messages": [
        {"role": "user", "content": "Hello!"}
    ],
    "stream": true
}

# Streaming response with SSE
response = requests.post(url, headers=headers, json=payload, stream=True)

for line in response.iter_lines():
    if line:
        print(line.decode('utf-8'))

3. File Upload & Management

Persistent file storage for use across requests:

POST /v3/upload

Upload once, use everywhere:

import requests

# Upload file
url = "https://api.edenai.run/v3/upload"
headers = {"Authorization": "Bearer YOUR_API_KEY"}

files = {"file": open("document.pdf", "rb")}
data = {"purpose": "ocr-processing"}

response = requests.post(url, headers=headers, files=files, data=data)
file_id = response.json()["file_id"]

# Use file in OCR request
ocr_response = requests.post(
    "https://api.edenai.run/v3/universal-ai",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model": "ocr/financial_parser/google",
        "input": {"file": file_id}
    }
)

4. API Discovery

Explore features and schemas programmatically:

GET /v3/info
GET /v3/info/{feature}
GET /v3/info/{feature}/{subfeature}

import requests

# List all features
response = requests.get(
    "https://api.edenai.run/v3/info"
)

features = response.json()
print(features)  # {"text": [...], "ocr": [...], "image": [...]}

V3 vs V2: Key Differences

Aspect	V2	V3
Architecture	Multiple feature-specific endpoints	Single universal endpoint + LLM
Provider Format	Body parameter	Provider string in model field
LLM Streaming	Optional	Mandatory (always SSE)
File Handling	Inline uploads per request	Persistent storage with file IDs
API Discovery	Documentation only	Built-in `/v3/info` endpoints
OpenAI Compatibility	Custom format	Native OpenAI format

Model String Format

V3 uses a unified model string format:

feature/subfeature/provider[/model]

Examples:

text/ai_detection/openai/gpt-4
ocr/financial_parser/google
image/generation/openai/dall-e-3
translation/document_translation/deepl

Available Features

Text Analysis

AI Detection - Detect AI-generated content
Moderation - Content moderation and safety
Embeddings - Semantic search vectors
Spell Check - Grammar and spelling correction
Named Entity Recognition - Extract entities
Topic Extraction - Identify main topics
Plagiarism Detection - Check for duplicates

OCR (Optical Character Recognition)

Text Extraction - Extract text from images/PDFs
Identity Parser - Parse ID documents and passports
Invoice Parser - Extract structured invoice data
Resume Parser - Parse CV and resume data

Image Processing

Generation - Create AI images
Object Detection - Identify objects
Face Detection - Detect faces
Face Comparison - Compare face similarity
Background Removal - Remove backgrounds
Explicit Content Detection - NSFW detection
AI Detection - Detect AI-generated images
Anonymization - Blur faces for privacy
Deepfake Detection - Detect manipulated images
Image Embeddings - Visual similarity vectors

Translation

Document Translation - Translate documents

Quick Start Guide

1. Get Your API Key

2. Choose Your Approach

Option A: Universal AI (Recommended for non-LLM)

response = requests.post(
    "https://api.edenai.run/v3/universal-ai",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "text/moderation/openai",
        "input": {"text": "Content to moderate"}
    }
)

Option B: OpenAI-Compatible LLM

response = requests.post(
    "https://api.edenai.run/v3/llm/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "openai/gpt-4",
        "messages": [{"role": "user", "content": "Hello"}],
        "stream": True
    },
    stream=True
)

3. Handle File Uploads (Optional)

# Upload
files_response = requests.post(
    "https://api.edenai.run/v3/upload",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("doc.pdf", "rb")}
)
file_id = files_response.json()["file_id"]

# Use in requests
response = requests.post(
    "https://api.edenai.run/v3/universal-ai",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "ocr/financial_parser/affinda",
        "input": {"file": file_id}
    }
)

Authentication

All V3 API requests require Bearer token authentication:

Authorization: Bearer YOUR_API_KEY

Base URL

https://api.edenai.run/v3

Response Format

All V3 responses follow a consistent structure:

{
  "status": "success",
  "cost": 0.001,
  "provider": "openai",
  "feature": "text",
  "subfeature": "ai_detection",
  "output": {
    // Feature-specific output
  }
}

Getting Started

Ready to dive in? Here are your next steps:

Getting Started Guide - Learn V3 basics
Universal AI Guide - Use the universal endpoint
OpenAI-Compatible LLM - Chat completions
File Upload Guide - Persistent file storage
API Discovery - Explore programmatically

Need Help?

Getting Started: Introduction Guide
API Reference: Check the V3 API tab for detailed specs
Support: Visit Eden AI Support

Ready to get started with V3? Jump to the Getting Started Guide or explore the Universal AI Guide.

V3 Documentation

​Eden AI V3 API Documentation

​What’s New in V3?

​Key Innovations

​Core Endpoints

​1. Universal AI - Single Endpoint for Everything

​2. OpenAI-Compatible LLM

​3. File Upload & Management

​4. API Discovery

​V3 vs V2: Key Differences

​Model String Format

​Available Features

​Text Analysis

​OCR (Optical Character Recognition)

​Image Processing

​Translation

​Quick Start Guide

​1. Get Your API Key

​2. Choose Your Approach

​3. Handle File Uploads (Optional)

​Authentication

​Base URL

​Response Format

​Getting Started

​Need Help?

Eden AI V3 API Documentation

What’s New in V3?

Key Innovations

Core Endpoints

1. Universal AI - Single Endpoint for Everything

2. OpenAI-Compatible LLM

3. File Upload & Management

4. API Discovery

V3 vs V2: Key Differences

Model String Format

Available Features

Text Analysis

OCR (Optical Character Recognition)

Image Processing

Translation

Quick Start Guide

1. Get Your API Key

2. Choose Your Approach

3. Handle File Uploads (Optional)

Authentication

Base URL

Response Format

Getting Started

Need Help?