Monitor your Vercel AI SDK features in production.

AI features shipped with the Vercel AI SDK serve real users in your product. AgentPing wraps your calls so each one becomes a run record with cost, status and optional quality, attributed to the customer and feature.

Track your first AI workflow Read the TypeScript SDK docs

Production AI in Vercel AI SDK fails quietly.

A Vercel AI SDK feature lives in your product, called by real users. When the AI bill moves, you need to know which feature and which customer drove it, and when a feature starts returning weaker answers, you want to know before the support queue does.

Wire it up in a few lines.

Initialise once, then wrap the call. A streamed generation is still one clean run, and the cost is attributed to the customer and feature you tag.

Install

          install
          Vercel AI SDK
        

npm install @agentping/sdk

Instrument

          example · typescript
          Vercel AI SDK
        

import { init, run } from "@agentping/sdk";
import { generateText } from "ai";

init({ apiKey: process.env.AGENTPING_API_KEY, agent: "copilot" });

// One run per call, attributed to the customer and feature.
await run({ agent: "copilot", customerId: "acme-corp", feature: "summarise" }, async () => {
  return await generateText({ model, prompt: "…" });
});

Full setup, environment variables and options are in the TypeScript SDK docs.

What AgentPing tracks for Vercel AI SDK.

Cost per run, attributed to the customer and feature you tag.
Run status and latency for every AI call in the product.
Cost spike alerts when a feature breaks its baseline.
Output quality checks so a regression is caught early.
Streaming-aware: a streamed response is still one clean run record.

Read the TypeScript SDK docs Heartbeat webhook docs

What you see in the dashboard.

A run list for Vercel AI SDK, each row showing cost, status and latency, filterable by agent, customer and feature.
Cost by agent, customer and feature, so you can see which accounts and features drive AI spend, not just one provider total.
An incident the moment a scheduled run misses its window or a cost spike breaks its baseline, delivered to Slack, email, PagerDuty or a webhook.
A quality trend once you turn on scoring, so a regression in your Vercel AI SDK output shows up as a falling line, not a support ticket.

Does it handle streaming responses?

Yes. A streamed generation is captured as a single run with its tokens, cost and final output, so streaming does not fragment your cost or quality data.

Can I attribute cost to the end customer?

Yes. Tag the run with the customer and feature, and the cost of that AI feature rolls up per customer, so you can see whether your pricing covers the cost of serving them.

What does it cost to monitor Vercel AI SDK?

There is a free plan with no card and no time limit, enough to wire up your first agents. Paid plans start at $99/month with named limits and no metered billing, so the bill never surprises you. Annual billing is two months free.

Does AgentPing see my prompts and outputs?

Only if you choose to send them. By default AgentPing prices runs from model and token counts and tracks status and timing, which needs no prompt or output content. Payload capture for quality scoring is opt-in and configurable per agent.

Monitor your Vercel AI SDK AI workflows.

Send one run from Vercel AI SDK and see cost, status and latency. Then add an alert for cost spikes or missed runs.

Track your first AI workflow Read the TypeScript SDK docs

Spend, cost attribution → Verify, quality scoring → Pulse, live monitoring →