Vercel Agent Pricing

Vercel Agent uses usage billing for paid work. Existing Vercel Agent credit balances are used first. After existing credit is consumed, additional paid usage is billed on-demand.

Provider inference cost is charged at the underlying token rate with no markup.

The Vercel Token Rate is an additional $0.25 per million tokens for paid Agent work, including Chat, Code Review, and additional Agent Investigations. It is charged in addition to provider inference costs.

The Vercel Token Rate scales with the actual work each task requires. A quick question costs less than a deep investigation that reads your logs, deployments, configuration, and runtime data, spins up sandboxes, and writes across projects. You pay for the intensity of the work, not a flat fee regardless of what Agent did.

The Vercel Token Rate covers:

• Joining your project context: logs, deployments, configuration, and runtime data
• Custom model routing and execution across your projects
• Processing and infrastructure costs

The Vercel Token Rate applies to input, output, and cached tokens.

Simple requests, like finding a setting, explaining a DNS warning, or answering a docs question, are free for a limited number of messages during the beta.

Chat responses are billed on demand when:

• The response requires Vercel Agent to investigate, plan, or write code
• You continue using Chat after your included beta messages are used

Vercel Agent does not bill paid Chat work until an authorized team member enables usage billing. If usage billing is not enabled, Vercel Agent prompts for consent before paid work continues.

Rejecting a proposed plan does not bill the work described in that plan.

Code Review is billed on demand: provider tokens at the underlying rate with no markup, plus a Vercel Token Rate of $0.25 per million tokens. This is the same token-based pricing as paid Chat.

Agent Investigation includes 10 alert investigations per billing cycle with Observability Plus. After those are used, each additional investigation is billed on demand: provider tokens at the underlying rate with no markup, plus a Vercel Token Rate of $0.25 per million tokens. This is the same token-based pricing as paid Chat and Code Review.

Existing Vercel Agent credit balances are used before usage-based charges begin. New top-ups are no longer available through the dashboard for teams using usage billing.

Enterprise billing depends on the team's pricing model:

You can monitor Vercel Agent spending in the Agent section in the sidebar of your dashboard.

To view costs:

1. Go to the Agent tab.
2. Review your current Agent credit balance, if your team has existing credit.
3. View the usage and cost columns to see the cost of each Code Review, Agent Investigation, or paid Chat action.

If certain repositories, alerts, or Chat tasks consistently cost more, adjust your settings or usage patterns to control spend.

An authorized team member must enable usage billing before paid Agent work can continue after existing credit is consumed.

To enable or manage usage billing:

1. Go to your team's Billing settings.
2. Find Vercel Agent Usage Billing.
3. Enable usage billing if prompted.

To stop new Agent charges:

• Disable Vercel Agent Chat to stop new Chat sessions.
• Disable Code Review to stop automatic pull request reviews.
• Disable Agent Investigation to stop automatic alert investigations.