Now in Public Beta
Now in Public Beta
The Fastest Way to Deploy AI.
The Fastest Way to Deploy AI.
Paste a Hugging Face or Civitai link, get a live API in minutes. No DevOps required.
Paste a Hugging Face or Civitai link, get a live API in minutes. No DevOps required.
Select a model online
Select a model online
Paste link on RunGen.AI
Paste link on RunGen.AI
Select customizations
Select customizations
Deploy
Deploy
Text-To-Image
Language Models
Get an image-gen API for the model of your choice.
All it takes to setup an Image Generation API is a link from HuggingFace or CivitAI. You can even fine-tune it with custom LoRAs or embeddings.
flux.1-dev, SD-3.5 and others from $0.04 / min
Add LoRas and embeddings for free
Text-To-Image
Language Models
Get an image-gen API for the model of your choice.
All it takes to setup an Image Generation API is a link from HuggingFace or CivitAI. You can even fine-tune it with custom LoRAs or embeddings.
flux.1-dev, SD-3.5 and others from $0.04 / min
Add LoRas and embeddings for free
Easy to integrate
Access all models via an easy API
Our REST-API gets you started in just a few lines of code. If you have an existing project, we're also compatible with OpenAI clients.
RunGen.AI Inference API
Our Inference API is made to allow easy generation of images and text, and REST makes it compatible with your whole stack.
Compatible with OpenAI
import os, requests response = requests.post( "https://api.rungen.ai/app/7db6900a-3992-4193-a2e9-e9c...", headers={"x-api-key": os.env.get("RUNGEN_API_KEY")}, json={ "input": { "prompt": "Explain black holes." }, }, ) print(response.json())
Easy to integrate
Access all models via an easy API
Our REST-API gets you started in just a few lines of code. If you have an existing project, we're also compatible with OpenAI clients.
RunGen.AI Inference API
Our Inference API is made to allow easy generation of images and text, and REST makes it compatible with your whole stack.
Compatible with OpenAI
import os, requests response = requests.post( "https://api.rungen.ai/app/7db6900a-3992-4193-a2e9-e9c...", headers={"x-api-key": os.env.get("RUNGEN_API_KEY")}, json={ "input": { "prompt": "Explain black holes." }, }, ) print(response.json())
Easy to integrate
Access all models via an easy API
Our REST-API gets you started in just a few lines of code. If you have an existing project, we're also compatible with OpenAI clients.
RunGen.AI Inference API
Our Inference API is made to allow easy generation of images and text, and REST makes it compatible with your whole stack.
Compatible with OpenAI
import os, requests response = requests.post( "https://api.rungen.ai/app/7db6900a-3992-4193-a2e9-e9c...", headers={"x-api-key": os.env.get("RUNGEN_API_KEY")}, json={ "input": { "prompt": "Explain black holes." }, }, ) print(response.json())
Ready for production.
When you host your AI models with RunGen.AI, you will be production-ready from day one.
Solid encryption
With RunGen.AI, your data is encrypted in transit and at rest.
Solid encryption
With RunGen.AI, your data is encrypted in transit and at rest.
Solid encryption
With RunGen.AI, your data is encrypted in transit and at rest.
Trusted cloud providers
We only work with cloud providers who meet strict security standards - your data is in good hands.
Trusted cloud providers
We only work with cloud providers who meet strict security standards - your data is in good hands.
Trusted cloud providers
We only work with cloud providers who meet strict security standards - your data is in good hands.
Effortless scaling
Add or remove instances for your AI in a few clicks.
Effortless scaling
Add or remove instances for your AI in a few clicks.
Effortless scaling
Add or remove instances for your AI in a few clicks.
Built-in collaboration
Work with your team-members and delegate model management.
Built-in collaboration
Work with your team-members and delegate model management.
Built-in collaboration
Work with your team-members and delegate model management.
Fast support
We're really active in our discord community, and will be there for you by email and phone.
Fast support
We're really active in our discord community, and will be there for you by email and phone.
Fast support
We're really active in our discord community, and will be there for you by email and phone.
Use all the models from HuggingFace or CivitAI
To get started, all you need is a link to the model you want to use. We automatically configure it and benchmark performance to ensure inference runs smoothly.
To get started, all you need is a link to the model you want to use. We automatically configure it and benchmark performance to ensure inference runs smoothly.
