Use Orq.ai as the model control layer for the Vercel AI SDK. Route LLM calls through one OpenAI‑compatible endpoint, capture traces, monitor cost, and manage fallback behavior without rebuilding your Vercel AI routes, UI components, or server actions.
What is Vercel AI?
The Vercel AI SDK is a TypeScript/JavaScript library for building AI features in web apps, with streaming, React/Svelte integrations, and a unified client over multiple providers. It helps teams focus on product UX and agent behavior instead of wiring every HTTP call, retry, and streaming handler by hand.
How the integration works
Step 1
Point Vercel AI’s LLM client at Orq.ai’s router
Configure the AI client or OpenAI‑compatible backend you use in Vercel AI (for example your OpenAI or client instance) to use Orq.ai’s router base URL and API key instead of calling each provider directly. Your route handlers keep the same interface; Orq becomes the routing layer behind them.
Step 2
Keep logging in place while routing through Orq
Leave your existing app logging and monitoring as‑is while you send Vercel AI SDK model calls through Orq’s endpoint. Your app continues to emit logs for business logic and UI events, and Orq records LLM interactions, latency, and cost metrics, so you can see both application‑level and model‑level traces.
Step 3
Define routes, fallbacks, and policies in Orq
Create routes in Orq for key Vercel AI workflows (for example chat endpoints, agentic routes, or tool‑calling APIs) and assign them model tiers, fallback chains, and region/data policies. Your Vercel AI code sends each request to the configured Orq route, and Orq applies routing rules before invoking OpenAI, Anthropic, Gemini, or other models.
Step 4
Monitor, evaluate, and tune
Once connected, use Orq’s dashboards to watch latency, errors, and cost for Vercel AI workloads, and run evals or experiments on their traces. You can adjust routes, models, or prompt configurations centrally where supported, without changing your SDK integration or rewiring your routes.
Use Cases
Multi‑surface apps with real observability
Trace which route, tool call, and model contributed to a failed workflow or frustrating UX, combining your own app logs with Orq’s router‑level traces.
Cost‑aware internal tools and UIs
Route routine steps like simple chat, summarization, or search to lower‑cost models while keeping complex reasoning, multi‑tool orchestration, or safety‑critical flows on your strongest routes configured in Orq.
Eval‑driven UX and prompt improvements
Reuse failed conversations and slow interactions as eval inputs before shipping prompt, tool, or model changes, turning production telemetry into a continuous improvement loop.
Safer experimentation across providers
Test a new provider or model on a small share of Vercel AI traffic, then promote or roll back based on traces and evals, instead of editing each SDK client configuration or route handler by hand.
FAQ
Do I have to change my Vercel AI code to use Orq.ai?
In many cases, you can repoint the OpenAI‑style client the SDK uses (base URL, API key, and model name) to Orq’s router and keep your existing handlers, components, and tools as‑is, adding only minimal configuration instead of rewriting routes.
Does Orq.ai replace Vercel AI’s own runtime or framework?
No. The Vercel AI SDK remains your library for streaming, UI integration, and agent behavior. Orq.ai sits alongside it as the control plane for models, multi‑provider routing, cost tracking, and evaluation. You still design and run AI features with the Vercel AI SDK at the core, but you use Orq to see what they cost, which models they should call, and how LLM behavior compares across providers under the same user workflows.
Can I keep using my existing LLM providers with Vercel AI if I move to Orq.ai?
Yes. You can bring your existing provider keys into Orq.ai and route Vercel AI traffic through them, alongside any new models you add later. That way you centralize access, routing, and tracking without losing the SDK and provider setup you already rely on. Bring production controls to Vercel AI apps
