Vercel Agent Pricing
Vercel Agent charges the underlying provider inference rate with no markup, plus a Vercel Token Rate of $0.25 per million tokens.
| Feature | Included usage | Pricing |
|---|---|---|
| Chat | A limited number of simple requests during the beta | Provider inference at the underlying token rate with no markup, plus $0.25 per million tokens |
| Slack | A limited number of simple requests during the beta | Provider inference at the underlying token rate with no markup, plus $0.25 per million tokens |
| Code Review | None | Provider inference at the underlying token rate with no markup, plus $0.25 per million tokens |
| Vercel Agent Investigation | 10 investigations per billing cycle with Observability Plus | Additional investigations use provider inference at the underlying token rate with no markup, plus $0.25 per million tokens |
| Installation | No charge for installation | Standard usage charges for installed products still apply |
The Vercel Token Rate is $0.25 per million tokens for paid Vercel Agent work. It is charged in addition to provider inference costs and applies to input, output, and cached tokens.
The Vercel Token Rate covers:
- Joining your project context, including logs, deployments, configuration, and runtime data
- Custom model routing and execution across your projects
- Processing and infrastructure costs
The amount you pay depends on the work required. A quick question costs less than an investigation that reads logs and configuration, runs commands in a sandbox, or writes across projects.
Simple requests, such as finding a setting, explaining a DNS warning, or answering a documentation question, are included up to a limited number of messages during the beta.
A Chat response incurs charges when:
- The response requires Vercel Agent to investigate, plan, or write code
- You continue using Chat after the included messages are used
Selecting Cancel on a proposed plan does not run or charge for the work described in that plan.
Code Review uses provider inference at the underlying token rate with no markup, plus the Vercel Token Rate of $0.25 per million tokens. The cost varies based on the complexity of the changes and the amount of code Vercel Agent analyzes.
Observability Plus includes 10 investigations per billing cycle. Additional investigations use provider inference at the underlying token rate with no markup, plus the Vercel Token Rate of $0.25 per million tokens. The cost varies based on how much log and metric data Vercel Agent analyzes.
There is no charge for using Vercel Agent Installation. Standard usage charges for installed products, such as Web Analytics or Speed Insights, still apply.
To view Vercel Agent usage and costs:
- Select Agent in the top-right corner of the dashboard.
- Open Usage.
- Select a time range and review the usage and cost information for Chat, Code Review, and investigations.
If certain repositories, alerts, or Chat tasks consistently cost more, adjust your settings or usage patterns to control spending.
An Owner or Billing member can manage Vercel Agent billing from the team's Billing settings.
To reduce new Vercel Agent usage, manage each source of automatic usage separately:
- Disable Dashboard chat to prevent new dashboard conversations.
- Turn off automatic Code Reviews to stop automatic pull request reviews. Manual reviews and explicit
@vercelrequests remain available and can create paid usage. - Disable Vercel Agent Investigation to stop automatic alert investigations.
Manual investigations and investigation reruns remain available and can create paid usage. Review the Agent Usage page after you change a setting.
Was this helpful?
