Introduction

Vortik helps you manage and scale your LLM integrations without the hassle. It essentially provides a gateway, a prompt hub, and deep observability tools-all built to run fast.

Why Vortik?

As your app grows, juggling multiple providers, fighting unpredictable costs, and updating prompts becomes painful. Vortik simplifies this:

• Unified Gateway: A single endpoint that mimics the OpenAI SDK, but routes your requests to any provider.
• Prompt Hub: Manage prompts in the dashboard instead of hiding them in your code.
• Observability: Track tokens, latency, and costs out-of-the-box, powered by OpenTelemetry.
• Region-Aware: Keep your data within specific regions (like the EU or US) effortlessly.

Core Concepts

Understanding these three pieces will get you far:

The Gateway

It acts as a smart proxy between your app and the AI providers. You barely change any code-just point your SDK to Vortik, and you instantly get logs, telemetry, and multi-provider switching.

Prompt Injection

Instead of hardcoding a prompt string, you just pass a v-prompt-id header to Vortik. We'll automatically inject the system prompt you've saved in the dashboard before sending the request to the LLM.

Observability

Vortik automatically generates OpenTelemetry traces for your AI activity. It captures how many tokens were used, how long the model took, and links it all together so you can easily trace a slow response back to its origin.

---

Ready to give it a try? Check out the Quickstart Guide.