Metorial works with any model supported by Vercel's AI SDK. This guide shows you how to use different model providers while keeping access to all 600+ integrations.

Supported Providers

The AI SDK supports many providers out of the box:

• OpenAI (GPT-4, GPT-4o, GPT-3.5)
• Anthropic (Claude)
• Google (Gemini)
• Mistral
• And many more

Metorial works with all of them.

Using OpenAI Models

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

await metorial.withProviderSession(
  metorialAiSdk,
  { serverDeployments: ['your-deployment-id'] },
  async session => {
    const result = await generateText({
      model: openai('gpt-4-turbo'),
      messages: [{ role: 'user', content: 'Your prompt here' }],
      tools: session.tools
    });
  }
);

Using Anthropic Claude

import { anthropic } from '@ai-sdk/anthropic';

const result = await generateText({
  model: anthropic('claude-3-5-sonnet-20241022'),
  messages: messages,
  tools: session.tools
});

Using Google Gemini

import { google } from '@ai-sdk/google';

const result = await generateText({
  model: google('gemini-1.5-pro'),
  messages: messages,
  tools: session.tools
});

Choosing the Right Model

Different models have different strengths:

• GPT-4/GPT-4o: Excellent for complex reasoning and tool use
• Claude 3.5 Sonnet: Great for analysis and following instructions
• Gemini Pro: Strong multimodal capabilities
• Smaller models: Faster and cheaper for simpler tasks

Model Configuration

You can pass additional parameters to customize model behavior:

const result = await generateText({
  model: openai('gpt-4-turbo'),
  messages: messages,
  tools: session.tools,
  temperature: 0.7,
  maxTokens: 2000,
  topP: 0.9
});

API Keys

Make sure you have API keys for your chosen provider:

OPENAI_API_KEY=your-openai-key
ANTHROPIC_API_KEY=your-anthropic-key
GOOGLE_GENERATIVE_AI_API_KEY=your-google-key

The AI SDK will automatically use these environment variables.