Connect → Vercel AI SDK

Use AxForge with the Vercel AI SDK

The AI SDK is the TypeScript toolkit for AI in web apps and on the server. Its OpenAI-compatible provider points it at AxForge, and generateText, streamText and the rest work as usual.

Set it up

1. Install the SDK and the provider

   npm install ai @ai-sdk/openai-compatible

2. Make an AxForge provider

   import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
   import { generateText } from "ai";
   
   const axforge = createOpenAICompatible({
     name: "axforge",
     baseURL: "https://api.axforge.ai/v1",
     apiKey: process.env.AXFORGE_API_KEY,
   });
   
   const { text } = await generateText({ model: axforge("qwen3.8-27b"), prompt: "Say hello in five words" });
   console.log(text);

3. Run it

   node hello.mjs

   

Streaming

import { streamText } from "ai";

const result = streamText({ model: axforge("qwen3.8-27b"), prompt: "Count to five" });
for await (const part of result.textStream) process.stdout.write(part);

With axforge made as above. In a web app, hand the stream to the page the way the AI SDK's own docs show: nothing in that part changes for AxForge.

The settings

Which model for what: qwen3.8-27b is the everyday default and reads images, glm-5.3-flash thinks before it answers, mimo-v2.6-flash is the fastest.

Keep the key on the server. In a browser bundle it would be public.

Check that it works

The script prints an answer. The call shows in the console under API Keys → Recent calls within a minute.

When it does not work

Not sure which it is? The connection doctor makes seven small checks on your key and names the fix: irm https://dev.axforge.ai/assets/axforge-doctor.ps1 | iex in PowerShell, curl -fsSL https://dev.axforge.ai/assets/axforge-doctor.sh | bash on macOS and Linux.

Test a call says in one click whether a problem is your key, your balance or us.