Compatible (BYOK)

Use Vercel AI SDK with GlideflowAI.

A TypeScript toolkit for streaming AI features with a custom provider instance. Connect it through GlideflowAI's OpenAI-compatible API with a key you control.

Get a key

What this connection is for

Vercel AI SDK is a TypeScript toolkit for streaming chat, generation, and structured-output features in web applications. It suits product teams that want provider-aware primitives without giving up control of the model endpoint. A custom provider instance can be passed into the same application functions that render streams or generate text, keeping endpoint selection close to server configuration.

Choose AI SDK when your application needs its streaming abstractions, framework adapters, or typed generation helpers. It is less appropriate for a simple script where calling the OpenAI SDK directly is clearer. Keep the provider instance on the server and test streaming with your deployment runtime, because a local response can differ from an edge or serverless execution path.

Create an OpenAI provider with baseURL set to GlideflowAI's /v1 endpoint and apiKey read from a server secret. Call glideflow.chat with an exact catalog model ID, then test the application route that will actually stream or return the response. Confirm that the deployed route, rather than only a local script, reads the intended secret name. Vercel AI SDK is an independent project; this is a user-managed connection, not an endorsement or partnership.

Why pair it with GlideflowAI

AI SDK's custom provider instance lets a streaming UI use GlideflowAI without changing the generateText or streamText pattern around it.

That makes endpoint selection a server configuration concern while the product keeps its existing TypeScript response pipeline.

Setup

Use a new API key for the tool, select a model from the catalog, and begin with a small task. Do not put a key in a repository, screenshot, or shared configuration file.

1
Set the server-side key
Keep the gateway key in your framework's server environment rather than a browser-visible variable.
```
GLIDEFLOW_API_KEY=sk-your-key
```

Create a custom provider

Use createOpenAI with baseURL and pass the resulting chat model to AI SDK functions.

import { createOpenAI } from "@ai-sdk/openai";
import { generateText } from "ai";

const glideflow = createOpenAI({
  apiKey: process.env.GLIDEFLOW_API_KEY,
  baseURL: "https://api.glideflowai.com/v1"
});

const { text } = await generateText({
  model: glideflow.chat("glm-5.2"), prompt: "Say OK"
});

Need the endpoint basics? Read authentication, browse the model catalog, or compare pricing.

Frequently asked questions

Should I use createOpenAI or the default openai provider?

Use createOpenAI so you can set GlideflowAI's baseURL and apiKey; the default provider targets OpenAI's own endpoint.

Where should the AI SDK provider be constructed?

Construct it in server-side application code or a protected module, never in a browser component where GLIDEFLOW_API_KEY could be bundled.

How do I choose the model for streamText?

Pass glideflow.chat with an exact model ID, such as glideflow.chat("glm-5.2"), after confirming that ID through the gateway catalog.

Is this an official integration?

No. The connection is configured by you using a compatible API and does not imply sponsorship, endorsement, or a partnership.

Ready to connect Vercel AI SDK?

Create a key, use the setup above, and verify the connection on a small task before you scale it up.