LLMGateway Provider for Vercel AI SDK

Forked from https://github.com/OpenRouterTeam/ai-sdk-provider

The LLMGateway provider for the Vercel AI SDK gives access to over 300 large language model on the LLMGateway chat and completion APIs.

AI SDK v4 & v5 support

• For AI SDK v4 or lower, use @llmgateway/[email protected].
• For AI SDK v5, use @llmgateway/[email protected].

Setup

# For pnpm
pnpm add @llmgateway/ai-sdk-provider

# For npm
npm install @llmgateway/ai-sdk-provider

# For yarn
yarn add @llmgateway/ai-sdk-provider

Provider Instance

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

import { llmgateway } from '@llmgateway/ai-sdk-provider';

Example

import { llmgateway, createLLMGateway } from '@llmgateway/ai-sdk-provider';
import { generateText } from 'ai';

const llmgateway = createLLMGateway({
  apiKey: process.env.LLM_GATEWAY_API_KEY,
});

const { text } = await generateText({
  model: llmgateway('openai/gpt-4o'),
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
});

console.log(`response: ${text}`);

Supported models

You can find the latest list of models supported by LLMGateway here.