Skip to main content
Braintrust integrates with Vercel in two ways: through the Vercel AI SDK for code-based tracing, and through the Vercel Marketplace for dashboard-based observability.

​
Setup

Choose your integration method based on your needs:
MethodBest forSetup
Vercel AI SDKFine-grained control over tracing, selective instrumentationInstall packages + add code
Vercel MarketplaceQuick setup, automatic tracing of all AI callsConfigure in Vercel dashboard

​
Option 1: Vercel AI SDK

Install the Braintrust SDK alongside the Vercel AI SDK. The Braintrust SDK supports Vercel AI SDK v3, v4, v5, and v6. 
# pnpm
pnpm add braintrust ai
# npm
npm install braintrust ai

​
Option 2: Vercel Marketplace

Install the Braintrust integration from the Vercel Marketplace. No package installation required.

​
Trace with Vercel Marketplace

The Vercel Marketplace integration provides automatic tracing for all AI calls in your Vercel applications with minimal setup.

​
Installation steps

  1. Visit the Vercel Marketplace listing and select Install
  2. Create or link your Braintrust account
  3. Select a plan (Free or Pro) and create a project name
  4. Select Add Drain to configure trace collection

​
Configure log drain

In the Add Drain panel:
  1. Select Traces and Next
  2. Choose which Vercel projects to trace (All Projects or specific projects)
  3. Set the sampling rate for trace collection

​
Enable OpenTelemetry

In your Next.js project, create an instrumentation.ts file and call registerOtel. See the Vercel OpenTelemetry docs for details.

​
Trace with Vercel AI SDK

The Braintrust SDK provides native support for the Vercel AI SDK, automatically tracing AI calls with full input/output logging, metrics, and tool execution.

​
Basic tracing

Use wrapAISDK to wrap the Vercel AI SDK functions (generateText, streamText, generateObject, streamObject).
trace-vercel-ai-sdk.ts
import { initLogger, wrapAISDK } from "braintrust";
import * as ai from "ai";
import { openai } from "@ai-sdk/openai";

initLogger({
  projectName: "My AI Project",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const { generateText } = wrapAISDK(ai);

async function main() {
  // This will automatically log the request, response, and metrics to Braintrust
  const { text } = await generateText({
    model: openai("gpt-5-mini"),
    prompt: "What is the capital of France?",
  });
  console.log(text);
}

main().catch(console.error);

​
Tool calls

wrapAISDK automatically traces tool call suggestions from the LLM and the tool execution results.
trace-vercel-ai-sdk-tools.ts
import { initLogger, wrapAISDK } from "braintrust";
import * as ai from "ai";
import { openai } from "@ai-sdk/openai";
import { z } from "zod";

initLogger({
  projectName: "Tool Tracing",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const { generateText } = wrapAISDK(ai);

async function main() {
  // Tool executions are automatically wrapped and traced
  const { text } = await generateText({
    model: openai("gpt-5-mini"),
    prompt: "What's the weather like in San Francisco?",
    tools: {
      getWeather: {
        description: "Get weather for a location",
        inputSchema: z.object({
          location: z.string().describe("The city name"),
        }),
        execute: async ({ location }: { location: string }) => {
          // This execution will appear as a child span
          return {
            location,
            temperature: 72,
            conditions: "sunny",
          };
        },
      },
    },
  });

  console.log(text);
}

main().catch(console.error);

​
Streaming with tools

You can also use streamText for streaming responses with tool calls:
trace-vercel-ai-sdk-streaming.ts
import { initLogger, wrapAISDK } from "braintrust";
import * as ai from "ai";
import { openai } from "@ai-sdk/openai";
import { z } from "zod";

initLogger({
  projectName: "Streaming Tool Tracing",
  apiKey: process.env.BRAINTRUST_API_KEY,
});

const { streamText } = wrapAISDK(ai);

async function main() {
  const result = streamText({
    model: openai("gpt-5-mini"),
    prompt: "What is 127 multiplied by 49?",
    tools: {
      calculate: {
        description: "Perform a mathematical calculation",
        inputSchema: z.object({
          operation: z.enum(["add", "subtract", "multiply", "divide"]),
          a: z.number(),
          b: z.number(),
        }),
        execute: async ({ operation, a, b }) => {
          switch (operation) {
            case "add": return a + b;
            case "subtract": return a - b;
            case "multiply": return a * b;
            case "divide": return b !== 0 ? a / b : 0;
          }
        },
      },
    },
    maxToolRoundtrips: 2,
  });

  for await (const delta of result.textStream) {
    process.stdout.write(delta);
  }
}

main().catch(console.error);

​
Resources