Skip to content
← All connectors
AI

DeepSeek

Use DeepSeek with AI apps and agents through Vercel Connect. Follow a complete setup guide for secure runtime access.

Create Connector

  1. Install the skill

    $ npx skills add vercel/vercel-plugin --skill vercel-connect

  2. Connect to DeepSeek

    Via CLIVercel Dashboard(opens in new tab)
    $ vercel connect create deepseek --name acme-deepseek

  3. Use its data in agents(opens in new tab) and apps(opens in new tab)

    import { getToken } from '@vercel/connect';
    

    const token = await getToken('deepseek/acme-deepseek');

Use DeepSeek in apps and agents

DeepSeek chat and reasoning models

Why use Vercel Connect with DeepSeek?

  • Credentials on demand

    Request DeepSeek credentials only when your application or agent needs them instead of copying secrets into application code.

  • Access for the right subject

    Keep app-scoped DeepSeek access behind a reusable connector controlled by your team.

  • Centralized credential management

    Manage DeepSeek credentials in one place and retrieve them through a consistent runtime API.

  • Vercel-native controls

    Bind connections to the projects and environments that need them while Vercel OIDC authenticates each runtime request.

Use DeepSeek with your stack

Follow a complete setup for the Connect SDK or a supported agent framework.

Add DeepSeek to an existing Vercel application with the Connect SDK.

  1. Install the Connect SDK

    npm install @vercel/connect

  2. Create the DeepSeek connector

    Run these commands from the project that will use the connection.

    vercel link
    vercel connect create deepseek --name acme-deepseek
    vercel env pull

  3. Request DeepSeek credentials

    app/api/route.ts
    import { getToken } from '@vercel/connect';
    

    const token = await getToken('deepseek/acme-deepseek');

More connectors like DeepSeek

Browse all connectors