Skip to content

Vercel AI SDK

AI features in TypeScript applications – with the model that fits your task and your data protection requirements.

dectria builds AI features in TypeScript applications with Vercel's AI SDK: answers that appear live in the interface, structured data following a fixed schema, tool calls, and agents that use functions of your systems.

We use the AI SDK in production in our own products, with Azure OpenAI in the EU, with Anthropic Claude and with local models via Ollama.

The AI SDK is one building block of our AI integration. We decide per use case which model and provider fit – based on quality, cost and data protection.

Official website Michael Jauk Your contact Michael Jauk Contact for AI & data

What is the AI SDK – and when is it worth it?

The AI SDK is an open-source TypeScript toolkit from Vercel that lets applications use language models from different providers through one interface: for text, structured data, tool calls and agents. It runs in Node.js and in frameworks such as Next.js, React, Vue and Svelte.

It is worth it when a TypeScript application uses several models, needs to stream answers or needs agents with tools. It is less worth it when only a single, simple call to one provider is needed – or when the backend runs in Python.

Direct provider API, AI SDK or AI SDK with AI Gateway?

Direct provider APIAI SDKAI SDK with AI Gateway
Switching providersadapt code per providerchange the model reference, application code stays the samechange the model reference, centrally in the gateway
Provider outagehandle it yourselfhandle it yourselfautomatic switch to another provider
Data pathdirectly to the providerdirectly to the providervia Vercel (a US company) to the provider; prompts not stored by default
Suited forone provider, simple callsapplications with several modelsseveral providers with failover

Capabilities

What We Build with Vercel AI SDK

Streaming Responses Structured Output with Zod Schemas Tool Calling & Agents MCP Integration Azure OpenAI / Claude / Ollama Vercel AI Gateway Embeddings for Vector Search Chat Interfaces with AI SDK UI Measuring Usage & Cost per Request Guardrails & Evaluation

Use Cases

Typical Use Cases

Text Features in SaaS Products

Summarizing, rephrasing and translating directly in the application, with answers that appear live instead of after a long wait.

Assistants with Tools

Assistants that query data and prepare actions via tool calls or MCP – with user approval for critical steps.

Structured Data Extraction

The model returns data following a fixed schema; the application validates it automatically and fills forms or databases.

FAQ

Vercel AI SDK FAQ

Why the AI SDK instead of a single provider's SDK?
Because applications rarely stay with one model. With the AI SDK, we write streaming, structured output and tool calls once and use them with different providers. Provider-specific features remain available where they are needed.
Does the AI SDK work with local models?
Yes. Community providers connect local models from Ollama, so data does not leave your network. Local models are smaller than the large cloud models – we test with your real tasks beforehand whether the quality is sufficient.
How do the AI SDK and the Vercel AI Gateway relate?
The AI Gateway is an optional Vercel service through which the AI SDK reaches models from many providers. It switches providers automatically during outages and does not store prompts by default. Requests pass through Vercel, a US company. If data must stay strictly in the EU, we connect Azure OpenAI directly.
Can the AI SDK be added to existing applications?
Yes, to Node.js backends as well as Next.js or React applications. We usually start with a single feature, such as a summary, measure quality and cost, and only then expand.

Every project starts with a conversation.

Let us talk about your individual needs and goals.

Start a project