Vercel AI Gateway adds a priced Trace Drains add-on
AI Gateway now offers Trace Drains, forwarding an OpenTelemetry trace of every request to a customer's own observability tool for $0.05 per 1,000 traces plus $0.50 per GB of trace egress on Pro and Enterprise.
AI Gateway add-on surcharges were limited to Custom Reporting, provider allowlist, and zero data retention (ZDR).
AI Gateway adds Trace Drains: $0.05 per 1,000 AI Gateway Traces + $0.50 per 1 GB trace egress (Pro and Enterprise), billed through the account's Drains usage rather than AI Gateway Credits.
Vercel’s AI Gateway pricing docs (last updated August 1, 2026) added a new Trace Drains add-on alongside the existing Custom Reporting, provider allowlist, and Zero Data Retention surcharges. Trace Drains forwards an OpenTelemetry trace of every AI Gateway request to the customer’s own observability tooling, and bills on two meters — the number of trace events delivered and the volume of trace data transferred.
The pricing mirrors the core platform’s existing Log Drains rate ($0.50 per 1 GB), extending the same drains mechanism to AI Gateway telemetry specifically. Unlike per-token AI Gateway usage, Trace Drains charges post against the team’s general Drains usage rather than depleting the AI Gateway Credits balance, and Pro plans include no free allowance for either meter — charges start with the first delivered trace.
v0 Mini and v0 Pro token prices are cut (Mini input $1→$0.20, output $5→$1.20; Pro input $3→$2, output $15→$10 per 1M tokens); v0 Max and Max Fast are unchanged. AI Gateway adds a Trace Drains SKU ($0.05/1K traces + $0.50/GB egress) plus Enterprise invoice billing. Custom Environments gets published overage pricing ($50/month per pack of five) for the first time. Vercel Sandbox concurrency quota rises from 2,000 to 10,000 on Pro/Enterprise and vCPU allocation moves to a dynamic quota (max 5,000/min). Core platform pricing (Pro $20/seat, eight dimensions) is unchanged.