Vercel AI Gateway
Explore Vercel AI Gateway models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Vercel AI Gatewayvercel-ai-gateway
These privacy labels describe Vercel AI Gateway, the upstream model provider. ZDR is a retention policy; verified confidential inference additionally requires attested provider compute and end-to-end encryption.
| Provider | Vercel AI Gateway |
|---|---|
| Routing status | Active |
| Provider website | https://vercel.com/ai-gateway |
| Models | 1 public model |
| Credits routes | 1 |
| Zero data retention | not claimed |
| Verified confidential inference | Not verified |
| Policy note | Fallback route for TypeSafe AI's Jev decision model, through Vercel AI Gateway's /v1/evaluate endpoint. A request served here transits two third parties (Vercel, then TypeSafe). No contractual ZDR, confidential-compute, or E2EE claim is tracked for this route. Policy source |
Models served by Vercel AI Gateway.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
typesafe-ai/jevTypeSafe AI Jev |
— | 32,000 | $0.04431/1M | Not published | selected route |
Questions
Does Vercel AI Gateway have zero data retention?
TrustedRouter does not currently mark Vercel AI Gateway as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Vercel AI Gateway end-to-end encrypted?
TrustedRouter does not currently mark Vercel AI Gateway as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Vercel AI Gateway models are available through TrustedRouter?
This page currently lists 1 public Vercel AI Gateway model, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.