Skip to main content

Introducing Friendli Dedicated Endpoints

Friendli Dedicated Endpoints (previously known as PeriFlow Cloud) gives you the reins to explore the full potential of your custom generative AI models on the hardware of your choice, whether you're crafting innovative eloquent texts, generating stunning images, or even more.

What are Friendli Dedicated Endpoints?

Don't be limited to pre-trained models. Friendli Dedicated Endpoints lets you take center stage:

  • Seamless Serving, Powered by the Friendli Engine: Experience the magic of the Friendli Engine, our patented GPU-optimized serving technology. Sit back and watch as your models come to life with automatically optimized performances, orchestrated seamlessly by Friendli Dedicated Endpoints.
  • Choose or Upload Your Model: Use your own custom models that are tailored to your specific needs and purposes. Otherwise, simply choose from the open-source models available on HuggingFace. Text generation, image creation, code synthesis – the possibilities are limitless.
  • Control Your Instance: Select the perfect GPU for your model. The GPU resources are dedicated entirely to your generative AI models. No sharing is required.
  • Per-second Billing, Worry-free Optimization: Focus on your creative pursuits, not cost management. Pay only for the seconds your model runs, eliminating the burden of manual optimization. Let Friendli Dedicated Endpoints handle the heavy lifting.
  • Proven Reliability for Real-World Success: Trusted by leading companies, Friendli Dedicated Endpoints delivers robust performance for even the most demanding workloads.

Getting Started with Friendli Dedicated Endpoints:

Ready to step up your generative AI game? Getting started is as simple as:

  1. Sign Up for a Free Account: Experience the power of Friendli Dedicated Endpoints risk-free.
  2. Choose or Upload Your Model: Harness your own custom-trained creation or simply select an open-source model.
  3. Launch Your GPU Instance: Select the perfect GPU for your model.
  4. Get Your Endpoint Address: Your gateway to unleashing your model's magic.
  5. Fine-tune Your Model: Optionally, you can fine-tune your generic model for your specific needs.
  6. Send Your Input: Prompt your model, send your queries, and let your creativity flow.
  7. Witness the Magic: Sit back and marvel as your custom model delivers stunningly fast outputs, tailored to your specific needs.

Friendli Dedicated Endpoints is more than just an AI serving platform - it's a launchpad for your creative ambitions. Dive into the website ( and blog ( to discover deeper insights, use cases, and customer testimonials.

In our documentations, you can find how you can (1) manage your projects and (2) models, and (3) make them come to life on your endpoints. To quickly have a look at our service, take a look at our quickstart document.

Reserve your own GPUs for your model! It's time to run your own models cost-efficiently with Friendli Dedicated Endpoints!

Additional Resources: