Hellas

Announcing Hellas Gate

Today we're launching Hellas Gate. Right now, it's an LLM gateway similar to OpenRouter, LiteLLM, and others, allowing you to access models from many different providers through a central API.

But this is table stakes.

We're aiming for something a little different: empowering individual devs, not enterprises. Here's a quick taste of our roadmap, and how we're planning to do that.

Local Compute

First up, we're making your local LLM accessible from anywhere. Think "tailscale for your home GPU".

You will be able to:

  • Access your own vLLM/Ollama API from anywhere
  • Pool shared compute resources with friends
  • Inspect, debug, and modify the prompts and chats made by your local tools

... and more to come.

Virtual Models and Smart Routing

Next up: virtual models and smart routing. Our aim here is to save you money, and level up your tools so they use the best models for any given task.

Writing some SQL? Use a cost-effective SQL fine-tune.

Paying Anthropic $10 for RAG with claude-cli? Use your local Qwen instance instead.

Here's how it works.

Model Aliases

  • Create a model alias like myusername/coding-rag.
  • Configure routing this alias in the Hellas dashboard. For example, have it always use QwQ-32B on your local GPU.
  • Configure your local tools to use the model myusername/coding-rag for RAG

Want to change things later? It's managed in one central place: edit your alias in the dashboard. No fiddling with all your different tool configs!

Smart Routing

Model aliases aren't just for picking one model. You can set rules to route to different models dynamically based on criteria. For example, let's say we want to use DeepSeek, but only when during off-peak times for lower cost.

Achieve this, by configuring the myusername/coding-rag alias with price limits.

Other filters and options in smart routing:

  • Geography (for data privacy)
  • Providers (e.g., "OpenAI models only")
  • Attributes (e.g., "Best model for coding")

... and more to come.

Conclusion

We're constantly improving Gate. If you have questions, feedback, or just want to hang out, come talk to us on discord.

Back to Blog