Hi there,

It’s time for a new and exciting release! We have been working very hard on Eden AI, mainly to improve our most popular features: LLM Chat and RAG!

We are working on even more improvements and some very exciting new features 🤩

New Features and Enhancements

RAG Custom Chatbot V2!

We released a new version of our Custom Chatbot RAG feature.

✅Improved User Experience – A cleaner, more intuitive interface to help you build faster.

🧠More LLM Options – Access a wider range of language models to fine-tune your results.

📁Smarter Data Importation – Easily upload and manage files, URLs, and texts.

🧩Advanced Chunk Management – Better handling of your documents for more accurate answers.

⚡ Faster Performance – Speed and stability upgrades for smoother execution.

...and much more under the hood.

👉 Try the new RAG version now

🎬 Check our complete video tutorial

New LLM Chat Endpoint

We’ve just released a new LLM chat endpoint:

👉 **https://api.edenai.run/v2/llm/chat**

This endpoint gives you unified access to all major LLM providers through a single OpenAI-compatible interface.

✅ Supported providers: OpenAI, Anthropic, Google, Mistral, Deepseek, Perplexity, Cohere, Amazon Bedrock, Qwen, xAI, Microsoft Azure

🔧 Key features:

• OpenAI-compatible format – works out of the box with most tools and SDKs
• Supports both text and multimodal models
• Unified schema across providers to simplify model switching
• Fallback model parameter – ensure continuity by specifying a secondary model if the primary one fails

This endpoint is optimized for flexibility and production reliability. You can easily A/B test providers or build robust workflows with automatic failover.

📚 Full docs available here: https://docs.edenai.co/reference/llm_llm_chat_create

🎬 Check our complete video tutorial

Here is our migration guide to switch from old to new endpoint: https://docs.edenai.co/docs/️-migration-tutorial-to-v2llmchat

Data Privacy Bot

We added a Data Privacy Bot in Eden AI platform. We often receive a lot of questions regarding AI providers data privacy policies. We thought it would be great to offer Eden AI users the possibility to get direct answers to all their questions regarding data privacy so we added this bot!

You can select providers and ask questions regarding your selection 👉 https://app.edenai.run/v2/data-policy

New Cost Management Interface and endpoints

We've redesigned the cost management interface to make it clearer and easier to use. You can now better understand your usage, track spending, and optimize costs more efficiently.

What are we cooking for the next release? 🧑‍🍳

Custom Prompt creation and versioning

We are working on a new and exclusive very powerful feature: Custom Prompt creation and versioning. It will allow you to create prompts using all the latest LLM models, save them, create different versions, choose which version to put in production, customize output format, analyze prompt performance and accuracy, and much more…

Stay tuned!

Bug Fixes

• Old workflows access
• ID Parser issue
• Microsoft Text to speech issue
• Anthropic issue
• ReadyRedact issue

We hope these updates enhance your experience with Eden AI and empower you to achieve more with our platform. Thank you for your continued support and feedback.

Do not hesitate to suggest ideas and features on our open roadmap!

Jérémy - The product guy

Hi there,

Hi there,

We’ve just released a new LLM chat endpoint:

👉 https://api.edenai.run/v2/llm/chat

This endpoint gives you unified access to all major LLM providers through a single OpenAI-compatible interface.

✅ Supported providers:

• OpenAI
• Anthropic
• Google
• Mistral
• Deepseek
• Perplexity
• Cohere
• Amazon Bedrock
• Qwen
• xAI
• Microsoft Azure
• Groq

🔧 Key features:

• OpenAI-compatible format – works out of the box with most tools and SDKs
• Supports both text and multimodal models
• Unified schema across providers to simplify model switching
• Fallback model parameter – ensure continuity by specifying a secondary model if the primary one fails

This endpoint is optimized for flexibility and production reliability. You can easily A/B test providers or build robust workflows with automatic failover.

📚 Full docs available here

🎬 Check our complete video tutorial

Here is our migration guide to switch from old to new endpoint; https://docs.edenai.co/docs/%EF%B8%8F-migration-tutorial-to-v2llmchat

Let us know if you need help with integration or want to give feedback.

Best,

Eden AI Team

Hi there,

We’re excited to announce that we’ve just launched a brand new version of our Retrieval-Augmented Generation (RAG) feature — and it’s packed with improvements!

Here’s what’s new:

✅ Improved User Experience – A cleaner, more intuitive interface to help you build faster.
🧠 More LLM Options – Access a wider range of language models to fine-tune your results.
📁 Smarter Data Importation – Easily upload and manage files, URLs, and texts.
🧩 Advanced Chunk Management – Better handling of your documents for more accurate answers.
⚡ Faster Performance – Speed and stability upgrades for smoother execution.
...and much more under the hood.

Whether you're building customer support agents or knowledge assistants, this version makes it easier and more powerful than ever.

👉 Try the new RAG version now

🎬 Check our complete video tutorial

We’d love to hear what you think!

Best,

Eden AI Team

Hi there,

It’s been a long time since our last release! We have been working very hard on Eden AI, making the platform and APIs more robust and performant. We also developed a way to release new models just a few minutes after their official launch (as we did for Claude 3.7 sonnet and GPT-4.5).

We are working on even more improvements and some very exciting new features 🤩

New Features and Enhancements

New Chat Models

We've implemented several new models in our Chat and Multimodal Chat APIs:

• OpenAI GPT-4.5 and o3-mini
• Claude 3.7 Sonnet
• Deepseek models R1 and V3
• xAI models grok-2 and grok-2-vision
• Mistral Multimodal model: pixtral-large-latest
• Qwen 2.5-72B-Instruct-Turbo
• Microsoft WizardLM-2-8x22B
• All Amazon Nova models (Pro, Lite, Micro)

New provider on Video Question Answering! 📽️

Video Question Answering is one of our latest popular API, so we wanted to add alternatives to Gemini models: we added Amazon Nova Pro model this API.

xAI grok-2 is available on Text features!

Grok-2 model performs very well in different LLM benchmarks. We wanted users to access it for text analysis tasks like: sentiment analysis, summarization, topic extraction, translation, named entity recognition, code generation, anonymization, etc.

New feature: Image Deepfake Detection!

We were already offering Image AI detection API on Eden AI but we wanted to provide something more specialized for detecting AI-generated faces. That’s why we added SightEngine’s Deepfake detection API!

Create API key and Monitor usage through API! 🔑

On Eden AI you can create multiple API keys in case you want to be able to track and monitor consumption of each users / customer or each project you have. You can now create API keys automatically through our new API endpoint, and also check consumption and credit left through our cost monitoring API.

What are we cooking for the next release? 🧑‍🍳

RAG Custom Chatbot V2!

We are currently working on a new version of our RAG feature. New intuitive UX, improve file and URL embeddings, multimodal RAG, new embedding models, more chunk management options and much more…

New LLM Chat Endpoint

We currently have two different endpoints, one for LLM supporting text input only and one for Multimodal LLMs. Those two endpoints have different models and structure, which is not always easy to use.

We are working on a new llm/chat endpoint that will support all the latest LLM models, multimodal or not —one endpoint, one document, one API and one output structure, for all models.

Plus, this endpoint will be OpenAI-compatible, which will simplify the integration of Eden AI API into third-party services.

Custom Prompt creation and versioning

We are working on a new and exclusive very powerful feature: Custom Prompt creation and versioning. It will allow you to create prompts using all the latest LLM models, save them, create different versions, choose which version to put in production, customize output format, analyze prompt performance and accuracy, and much more…

Stay tuned! 📲

We hope these updates enhance your experience with Eden AI and empower you to achieve more with our platform. Thank you for your continued support and feedback.

Do not hesitate to suggest ideas and features on our open roadmap!

Jérémy - The product guy

Hi there,

We’re excited to announce that OpenAI's latest model, GPT-4.5, is now live on Eden AI! You can use it for:

🔹 Chat → API docs
🔹 Multimodal Chat (text + documents) → API docs
🔹 RAG (Retrieval-Augmented Generation) → API docs

To call this model, simply use this value for the provider parameter:

openai/gpt-4.5-preview-2025-02-27

With Eden AI, you can compare OpenAI GPT-4.5 with other models and switch providers seamlessly—all through a single API.
​
We’re committed to staying up-to-date with the latest AI innovations to bring you the best models as soon as they launch.
​
Cheers
Taha

We understand that our previous pricing model—a mix of subscriptions and credit purchases—was overly complicated. And honestly, we get it. It wasn’t the easiest to understand or project costs.

After trying several ways to simplify it, we realized there was no magic fix. So, we made a bold decision: we’re removing monthly subscriptions entirely.

Looking back, this change aligns perfectly with our vision of making AI accessible to as many companies as possible. How can AI be truly accessible if pricing makes it hard to predict costs?

Our goal is simple: cost should never stand in the way of adopting AI. Now, let’s talk about what this means for you.

Access to ALL Eden AI features

You now get full access to all Eden AI features, no matter the size of your team or how many API calls you make each month. Here’s what that looks like:

• Unlimited seats: invite your entire team to collaborate on AI projects.
• Unlimited workflows: build as many workflows as you need to cover all your use cases.
• Unlimited executions: whether you make 10 or 10 million API calls, there’s no limit.
• Bring your API keys: already have accounts with model providers? Use your keys to avoid buying credits. Don’t have accounts? You can simply buy credits through Eden AI.
• Access to advanced features: bach processing & caching.

We believe in flexibility. Why pay for features you don’t use? With no subscriptions, you only pay for what you need, when you need it, with no commitments.

How do we make money?

Let’s address the obvious question: how do we stay viable without subscription revenue? The answer is simple: provider-side revenues.

If you don’t have API keys with model providers, you have to buy Eden AI credits to make API calls directly through us. Here’s why that works:

• For you: costs stay the same as if you went directly to the provider. We don’t add any extra fees.
• For us: thanks to the large volume of API calls made through Eden AI, we are able to negotiate better rates with AI vendors. This allows us to earn a margin on the discounted rates without increasing your costs.

A simpler future with Eden AI

This change goes beyond a simple pricing update. It’s a step toward creating a seamless, accessible AI platform that adapts to your needs. We’ve eliminated complexity so you can focus on what truly matters: building, innovating, and scaling with AI.

With unlimited access, transparent costs, and flexible usage, Eden AI is ready to grow with your company, no matter its size or goals.

We can’t wait to see what you’ll build next with Eden AI.

Thank you for your trust—it means a lot to our team.

Taha, CEO @Eden AI

The video generation API is now available on Eden AI. Developers can now easily integrate video generation into their application or process.

Now you can…

• Automate video generation directly from text or image input;
• Integrate video creation into your existing workflows;

How to make API call

1. You can use the API on its own, or combine it with other APIs by building a workflow;
2. Test performance & cost of different providers/models with the live testing interface;
3. Use code snippet and add custom parameters such as fallback_providers;

Code snippet:

import json
import requests

headers = {"Authorization": "api_key"}

url = "https://api.edenai.run/v2/video/generation_async"
payload = {"providers": "amazon", "text": "your prompt"}

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

result = json.loads(response.text)
print(result)

Available models

• Amazon Nova Reel: control visual style, rhythm and camera movements with natural language prompts.
• Other models will be available soon.

API doc

• API doc
• Model specifications (price, billing unit)
• Check out our development quickstart guide

Not a developer?

Use no-code platforms or app integrations to use the Eden AI API without writing a line of code.

Ready to get started? Try the video generation API today and unlock new AI capabilities!

Hi there,

Happy New Year! 🎉 We're kicking off 2025 with exciting updates: video generation, the return of our powerful AI Model APIs, and even more collaborative workflow features. Let's make this year full of innovation!

New features and enhancements

New Feature: Video Generation

Introducing video generation! You can now create high-quality videos using AI. Craft compelling video content with ease, directly from Eden AI Workflows or as a standalone API feature.

AI Models APIs Are Back! 🎉

Over the past months, we’ve focused on improving Workflows to make it a powerful tool for crafting, orchestrating, and deploying complex AI processes.

But we know that sometimes, simplicity is key. If you’re looking for a single AI feature with the same streamlined experience Eden AI is known for, you’re in luck: our standardized, easy-to-implement APIs are back!

• Live-test and use over 60+ AI features.
• No monthly fees – only pay for what you use.

Rediscover the simplicity and power of Eden AI's APIs today!

Workflow Improvements

Web Scraper Node

Extract data from websites with the new Web Scraper Node. Whether for competitive analysis, content gathering, or data enrichment, this node allows you to use web scraping in your AI workflows.

Workflow Sharing

Collaboration made easy!

Team members within the same organization can now view and edit each other’s workflows. This feature is designed to boost productivity and streamline collaborative efforts on Eden AI.

Additional Updates

No More Monthly Licenses – Pay Per Use Only!

We’re simplifying pricing. With no upfront monthly fees, you now only pay for what you use. Whether you're exploring APIs or crafting workflows, you can scale with confidence and cost-effectiveness. 😃

Bug Fixes

• Video Shot Detection interface
• Chat Multimodal code snippet
• TwelveLabs error
• Alephalpha error
• Base64 error
• Photoroom error
• LLM models on Document parsing features
• Summarization API

We hope these updates enhance your experience with Eden AI and empower you to achieve more with our platform. Thank you for your continued support and feedback.

Do not hesitate to suggest ideas and features on our open roadmap!

Jérémy - The product guy

Web scrapers and webhooks are now available on Eden AI workflow.

These tools available on workflow nodes enabling you to streamline data acquisition and create more efficient, automated workflows.

Web scrapers

Effortlessly extract structured data from websites to integrate into your workflows:

• Dynamic data extraction: specify target elements with URL and scrape real-time content from any website;
• Seamless RAG integration: directly pipeline scraped data to RAG system;

Webhooks

Webhooks enable event-driven communication between Eden AI workflows and external systems:

• Event triggers: activate workflows upon external events, such as data uploads or API responses;
• Bidirectional integration: send or receive data via incoming and outgoing webhooks;
• Third-party connectivity: easily connect external services;

Code snippet for workflow webhook:

import requests

headers = {"Authorization": "Bearer {api_key}"}

url = "https://api.edenai.run/v2/workflow/{workflow_id}/execution/"
files = {"video":open('/path/to/your/video.ext', 'rb')} 
payload = {
    "webhook_receiver": "https://webhook.site/fbfc569c-0cad-4e67-8c9f-019f78ab2ff7",
    "users_webhook_parameters": {"something": "an_id"}, 
    "send_webhook_data": true // this means to send full body or not
}
response = requests.post(url, files=files, data=payload, headers=headers)
result = response.json()

The addition of web scrapers and webhooks to Eden AI empowers developers with powerful tools for automating data workflows and enhancing AI integrations.

As always, feel free to reach out with feedback or questions. I’m here to help you make the most of Eden AI.

Samy, CTO @Eden AI