Vercel AI SDK - ScitiX

Vercel AI SDK is the TypeScript toolkit for building AI apps. Its @ai-sdk/openai-compatible provider connects to any OpenAI-compatible endpoint, so it runs on the ScitiX Model Inference API. Default model here is glm-5.2; see the Models page for the full list and pricing.

Configure

Create an API key on the ScitiX API Keys page and export it:

export SCITIX_API_KEY="<Your API Key>"

Install ai and @ai-sdk/openai-compatible, then create a ScitiX provider:

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { generateText } from 'ai';

const scitix = createOpenAICompatible({
  name: 'scitix',
  baseURL: 'https://api.scitix.ai/model-api/v1',
  apiKey: process.env.SCITIX_API_KEY,
});

Field	Description
`baseURL`	ScitiX OpenAI-compatible endpoint: `https://api.scitix.ai/model-api/v1`. The provider appends `/chat/completions`.
`apiKey`	Your ScitiX API key, read from the environment
`scitix('<id>')`	ScitiX model ID, e.g. `scitix('glm-5.2')`

Use @ai-sdk/openai-compatible, not @ai-sdk/openai. The latter targets OpenAI’s own API and defaults to the Responses API; the compatible provider is built for custom OpenAI-style endpoints like ScitiX. Choose a model with native tool calling for the SDK’s tool-calling / streamText tool features.

Verify

Generate text — a normal reply confirms the connection (verified on ai 7.0.62, @ai-sdk/openai-compatible 3.0.30):

const { text } = await generateText({
  model: scitix('glm-5.2'),
  prompt: 'In one short sentence, which model are you?',
});
console.log(text);
// → I'm GLM, a large language model developed by Z.ai.