Skip to main content

Documentation Index

Fetch the complete documentation index at: https://cerebrium.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

The Cerebrium + Vercel integration provides access to Cerebrium-deployed apps via REST endpoints from Vercel projects. Install it from the Vercel AI marketplace.

​
What this integration does

This integration provides:
  1. Automatic synchronization of Cerebrium API keys to one or more Vercel projects.
  2. HTTP access to Cerebrium endpoints from connected Vercel projects.

​
Authentication

The integration sets the following environment variables on the selected Vercel projects:
  • CEREBRIUM_JWT
The environment variables are set in the “preview” and “production” project targets. See the Vercel documentation for more on environment variables.

​
Installing the integration

  1. Click “Add Integration” on the Vercel integrations page.
  2. Select the Vercel account you want to connect with.
  3. (If logged out) Sign into an existing Cerebrium project, or create a new Cerebrium project.
  4. Select the Vercel projects that you wish to connect to your Cerebrium workspace.
  5. Click “Continue.”
  6. Back in your Vercel dashboard, confirm the environment variables were added by going to your Vercel project → Settings → Environment Variables.

​
Uninstalling the integration

Manage the Cerebrium Vercel integration from the Vercel dashboard under the “Integrations” tab. Remove the integration installation from there. Important: Removing an integration will delete the corresponding API token set by Cerebrium in your Vercel project(s).

​
Example

See the Mistral 7B with vLLM example for deploying to an auto-scaling endpoint. After deploying the app, the output includes the endpoint URL. Call it from a Vercel project: 
fetch(
  "https://api.aws.us-east-1.cerebrium.ai/v4/p-<YOUR PROJECT ID>/mistral-vllm/predict",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.CEREBRIUM_JWT}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      prompt: "What is the capital city of France?",
    }),
  },
)
  .then((response) => response.json())
  .then((data) => console.log(data))
  .catch((error) => console.error("Error:", error));
This example app takes a prompt as input and returns the model output.

​
Pricing

Requests to apps use usage-based pricing, billed at 1ms granularity. The exact cost per millisecond is based on the underlying hardware you specify. See the pricing page for current GPU prices.