Vercel Deep Infra IntegrationNative Integration

Deep Infra provides scalable andcost-effective infrastructure for deploying and managing machine learningmodels. It's optimized for reduced latency and low costs compared to traditionalcloud providers.

This integration gives you access to the large selection of available AI models and allows you to manage your tokens, billing and usage directly from Vercel.

You can use theVercel and Deep Infra integration to:

• Seamlessly connect AI models such as DeepSeek and Llama with your Vercel projects.
• Deploy and run inference with high-performance AI models optimized for speed and efficiency.

Deep Infra provides a diverse range of AI models designed for high-performance tasks for a variety of applications.

The Vercel Deep Infra integration can be accessed through theAI tab on yourVercel dashboard.

To follow this guide, you'll need the following:

• An existingVercel project
• The latest version ofVercel CLI
  pnpmyarnnpmbun

  pnpm i -g vercel@latest

1. Navigate to theAI tab in yourVercel dashboard
2. Select Deep Infra from the list of providers, and pressAdd
3. Review the provider information, and pressAdd Provider
4. You can now select which projects the provider will have access to. You can choose fromAll Projects orSpecific Projects
   • If you selectSpecific Projects, you'll be prompted to select the projects you want to connect to the provider. The list will display projects associated with your scoped team
   • Multiple projects can be selected during this step
5. Select theConnect to Project button
6. You'll be redirected to the provider's website to complete the connection process
7. Once the connection is complete, you'll be redirected back to the Vercel dashboard, and the provider integration dashboard page. From here you can manage your provider settings, view usage, and more
8. Pull the environment variables into your project usingVercel CLI
   terminal

   vercelenvpull

9. Install the providers package
   pnpmyarnnpmbun

   pnpm i @ai-sdk/deepinfra ai

10. Connect your project using the code below:
    Next.js (/app)Next.js (/pages)SvelteKitOther frameworks

    app/api/chat/route.ts

    // app/api/chat/route.ts
    import{ deepinfra}from'@ai-sdk/deepinfra';
    import{ streamText}from'ai';
    // Allow streaming responses up to 30 seconds
    exportconst maxDuration=30;
    exportasyncfunctionPOST(req:Request){
    // Extract the `messages` from the body of the request
    const{ messages}=await req.json();
    // Call the language model
    const result=streamText({
        model:deepinfra('deepseek-ai/DeepSeek-R1-Distill-Llama-70B'),
        messages,
    });
    // Respond with the stream
    return result.toDataStreamResponse();
    }
    

1. Add the provider to your project using theVercel CLIinstall command
   terminal

   vercelinstall deepinfra

   During this process, you will be asked to open the dashboard to accept themarketplace terms if you have not installed this integration before. You canalso choose which project(s) the provider will have access to.
2. Install the providers package
   pnpmyarnnpmbun

   pnpm i @ai-sdk/deepinfra ai

3. Connect your project using the code below:
   Next.js (/app)Next.js (/pages)SvelteKitOther frameworks

   app/api/chat/route.ts

   // app/api/chat/route.ts
   import{ deepinfra}from'@ai-sdk/deepinfra';
   import{ streamText}from'ai';
   // Allow streaming responses up to 30 seconds
   exportconst maxDuration=30;
   exportasyncfunctionPOST(req:Request){
   // Extract the `messages` from the body of the request
   const{ messages}=await req.json();
   // Call the language model
   const result=streamText({
       model:deepinfra('deepseek-ai/DeepSeek-R1-Distill-Llama-70B'),
       messages,
   });
   // Respond with the stream
   return result.toDataStreamResponse();
   }