Compatible (BYOK)

Use OpenAI SDK with GlideflowAI.

The official OpenAI client library pointed at a compatible chat endpoint. Connect it through GlideflowAI's OpenAI-compatible API with a key you control.

Get a key

What this connection is for

The OpenAI SDK is the direct client library for applications that use the OpenAI API shape from JavaScript, Python, and other supported languages. It suits engineers who want a small integration surface: construct a client, select a model, and make requests from their own application code. There is no extra workflow layer between the app and its chosen compatible provider.

Choose the SDK when your application needs precise control over request construction, retries, secret handling, and response handling. It is less useful when you need a visual workflow builder, a retrieval framework, or an evaluation harness out of the box. Keep the client server-side, especially for web applications, because a browser bundle must never expose a reusable gateway key.

The SDK accepts a baseURL override, so construct the client with GlideflowAI's /v1 endpoint and send a Chat Completions request using an exact model ID. Validate the integration with a minimal server-side request before layering on tools or streaming. Log only request metadata that is safe for your environment, never the complete authorization header. OpenAI SDK is an independent project; this is a user-managed connection, not an endorsement or partnership.

Why pair it with GlideflowAI

The OpenAI SDK's baseURL option makes GlideflowAI a small configuration change in an application that already uses the client.

That is useful for teams that want one client abstraction while selecting gateway models in deployment configuration rather than rewriting application logic.

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 key in your application environment
Use a project-local secret mechanism such as an uncommitted .env file in development or your deployment platform's secret store.
```
GLIDEFLOW_API_KEY=sk-your-key
```

Create a client with GlideflowAI's base URL

Use the OpenAI SDK's baseURL option and make a basic Chat Completions request.

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "glm-5.2",
  messages: [{ role: "user", content: "Say OK" }]
});

Need the endpoint basics? Read authentication, browse the model catalog, or compare pricing. For tool-specific troubleshooting, see the existing guide.

Frequently asked questions

Should the OpenAI SDK call Responses or Chat Completions?

Use the documented Chat Completions route for this gateway example; do not assume a client default will select an unsupported endpoint for a chosen model.

Can I expose GLIDEFLOW_API_KEY in a browser app?

No. Instantiate the SDK in a server route, server action, worker, or other protected runtime and keep the key in that runtime's secret store.

How do I check model IDs before deployment?

Authenticate a GET request to https://api.glideflowai.com/v1/models, then use the returned exact ID in the client configuration.

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 OpenAI SDK?

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