GMI Cloud Provider

The GMI Cloud provider offers access to open-weight language models through GMI Cloud's GPU inference platform, over an OpenAI-compatible API.

API keys can be obtained from the GMI Cloud console.

Setup

The GMI Cloud provider is available via the @ai-sdk/gmicloud module. You can install it with:

pnpm add @ai-sdk/gmicloud

Provider Instance

You can import the default provider instance gmicloud from @ai-sdk/gmicloud:

1
import { gmicloud } from '@ai-sdk/gmicloud';

For custom configuration, you can import createGmicloud and create a provider instance with your settings:

1
import { createGmicloud } from '@ai-sdk/gmicloud';
2

3
const gmicloud = createGmicloud({
4
  apiKey: process.env.GMI_CLOUD_APIKEY ?? '',
5
});

You can use the following optional settings to customize the GMI Cloud provider instance:

• baseURL string

  Use a different URL prefix for API calls. The default prefix is https://api.gmi-serving.com/v1.

• apiKey string

  API key that is being sent using the Authorization header. It defaults to the GMI_CLOUD_APIKEY environment variable.

• headers Record<string,string>

  Custom headers to include in the requests.

• fetch FetchFunction

  Custom fetch implementation.

Language Models

1
import { gmicloud } from '@ai-sdk/gmicloud';
2
import { generateText } from 'ai';
3

4
const { text } = await generateText({
5
  model: gmicloud('deepseek-ai/DeepSeek-V4-Flash-0731'),
6
  prompt: 'What is the capital of France?',
7
});

GMI Cloud serves an evolving catalog of open-weight models, so model ids are typed as string. Embedding and image models are not supported.

Error diagnostics

GMI Cloud's edge reports a generic banner in error.message on rejections and nests the backend engine's diagnostic in error.details. This provider unwraps the nested diagnostic, so AI_APICallError.message carries the engine's reason (e.g. The request is invalid: Invalid max_tokens value, the valid range of max_tokens is [1, 393216].) instead of Backend request failed with status 400.