When did Vercel AI Gateway become generally available?

Vercel AI Gateway reached general availability in August 2025. It is a hosted unified endpoint that fronts hundreds of models, welded to the Vercel AI SDK, with zero markup on tokens including bring-your-own-key, default zero data retention, provider allowlists on paid tiers, and automatic failover. It is strong for teams building on Vercel and is the default inference path for Vercel's own SDK.

Does Vercel AI Gateway keep an audit trail?

Its default posture is zero data retention, deleting prompts and responses after the request completes, which is a privacy stance rather than an audit stance. Its Custom Reporting add-on attaches tags and user IDs and is billed per write and per query, giving spend attribution rather than a tamper-evident decision record. There is no signed, independent per-decision audit record. A workload that has to prove what each AI call did needs that record produced by a layer built for it.

Can I self-host Vercel AI Gateway?

Vercel AI Gateway runs only as Vercel-hosted SaaS, and its OIDC authentication path assumes Vercel projects. Teams that need an in-VPC or on-prem deployment for regulated data, or that run workloads off Vercel, are the clearest candidates for an alternative, and the self-hostable options are TrueFoundry, Envoy AI Gateway, Kong, LiteLLM, agentgateway, and Bifrost.

What is the best alternative for regulated data?

For regulated data the deciding factors are where the layer runs and what it proves. A self-hosted router such as Envoy AI Gateway or Kong keeps traffic in your environment, and an identity-bound enforcement layer in front of it produces the classification and the signed per-decision record a regulator inspects. Another hosted SaaS gateway solves the routing question while keeping a third party in the path of every prompt, which is usually the thing a regulated team is trying to remove.

Do I have to replace Vercel AI Gateway completely?

An identity-and-audit requirement can be met by adding an enforcement layer at the AI request boundary while leaving routing in place. Hosting or data-residency requirements mean the routing layer itself needs a self-hosted replacement, with enforcement in front of it. The two decisions, where routing runs and where enforcement runs, are separable.

8 Vercel AI Gateway Alternatives by Deployment

Vercel AI Gateway alternatives fall into four usable groups: self-hosted routers for VPC deployment, enterprise API gateways, hosted multi-provider services, and an enforcement layer that produces identity-bound audit evidence. Vercel AI Gateway itself went generally available in August 2025. It fronts hundreds of models through https://ai-gateway.vercel.sh/v1, with budgets, usage monitoring, load balancing, and automatic failover. Its defining feature is integration: with the Vercel AI SDK, a bare model string like anthropic/claude-opus-4.7 auto-routes through the gateway, and it charges zero markup on tokens, including when you bring your own key.

Teams building outside Vercel usually need a different deployment boundary, not a different model catalogue. The eight options below separate self-hosting, multi-provider routing, and request-level evidence so the choice starts with the constraint that actually matters.

TL;DR

Choose a self-hosted router when VPC deployment or data residency determines the architecture. Choose a hosted multi-provider service when provider breadth and operational convenience matter more. Add request-boundary enforcement when each LLM call needs an authenticated identity, content policy, and an independent decision record.

What Vercel AI Gateway is, and what it does not do

Start with the governance it does have, because a fair comparison names it. Zero data retention is on by default, deleting prompts and responses after the request completes. You can restrict routing to verified zero-retention providers per request or per team, disallow prompt training, and configure a Provider Allowlist on Pro and Enterprise. Authentication uses dashboard API keys, which deactivate when the creating team member leaves, and Vercel OIDC tokens tied to a Vercel project with a twelve-hour validity.

Now the boundary of that model. Authentication is team and project scoped, so the gateway knows which project or key made a call, without an end-user identity propagated into a policy decision. There is no prompt-level classification across regulated data types. There is no signed, tamper-evident per-decision audit record. The Custom Reporting feature that attaches tags and user IDs is a paid add-on billed per write and per query, and it is spend attribution rather than an audit artifact. And the whole thing runs as Vercel-hosted SaaS, with no self-hosted deployment.

Who genuinely needs an alternative

Four situations, each concrete.

The team runs workloads off Vercel. The OIDC path assumes Vercel projects, so a multi-cloud or non-Vercel deployment loses the part that made the gateway convenient and is left routing prompts to a third-party endpoint.

The data is regulated and has to stay in a controlled environment. Vercel AI Gateway has no self-hosted or in-VPC mode. A workload under HIPAA, DORA, or a data-residency mandate that cannot send prompts to a Vercel-hosted endpoint needs a layer it can run itself.

The team needs identity-bound per-request policy. Project-scoped keys answer which project called. A regulated deployment often needs to answer which verified person or agent called, under which policy, which is a different primitive.

The team needs independent audit evidence. Default zero retention is a strong privacy posture, and it means the gateway is not the place a signed decision record lives. A workload that has to prove what each AI call did needs that record produced somewhere.

Eight alternatives, sorted by deployment and enforcement

Because the reason to leave Vercel AI Gateway is usually about where the layer runs and what it proves, I have sorted the alternatives by deployment and enforcement rather than by model count.

TrueFoundry. This self-hosted VPC option is a Kubernetes-native AI platform with a gateway as one module. The trade-off is platform adoption. Its controls include RBAC, budgets, guardrails, and a self-hosted control plane.

Envoy AI Gateway. This self-hosted Kubernetes gateway gives infrastructure teams routing they own. The project documentation covers its provider routing, MCP gateway, quota-aware multi-tenancy, and upstream authentication. See the full comparison for its request-boundary trade-offs.

Kong AI Gateway. Kong can run self-hosted or managed and extends an enterprise API platform to AI traffic. Its relevant controls are PII sanitization, prompt guards, RBAC, quotas, and audit features.

LiteLLM Proxy. LiteLLM offers a self-hosted or Cloud router with virtual credentials, budgets, guardrails, and management-plane audit on Enterprise. Teams using it should assess the proxy's current security posture as part of their operating model.

agentgateway. This self-hosted open-source project covers A2A and MCP authorization plus agent-traffic observability. It is relevant when agent protocol traffic is the deployment problem; its controls do not substitute for a per-request LLM enforcement record.

Cloudflare AI Gateway. Cloudflare provides hosted edge observability, caching, and rate limiting. Its DLP and Guardrails capabilities suit teams comfortable with another SaaS service in the prompt path.

OpenRouter. This hosted marketplace provides key-bound guardrails, budgets, allowlists, and broad model access. It remains a third party in the path of every prompt.

Bifrost (Maxim). Bifrost is a self-hosted open-source, Go-based routing choice with load balancing, virtual credentials, budgets, guardrails, and MCP support.

If the reason you are leaving Vercel AI Gateway is hosting or data residency, the self-hosted rows are the real candidates. If the reason is convenience or price, another hosted SaaS trades one dependency for another.

The layer none of these fully covers

Every product above routes traffic, and several enforce content policy. What none of them centers is the combination a regulated workload actually needs at the AI request boundary: per-request policy bound to a verified identity, prompt classification across PII, PHI, MNPI, and jurisdictional categories, a signed per-decision audit record held independently of the application, and fail-closed behavior on error. A gateway that binds identity into the decision and produces an independent record is a different layer than a router, even when both are called gateways.

DeepInspect

This is the gap DeepInspect closes, and it composes with a router rather than replacing one. A team leaving Vercel AI Gateway for a self-hosted stack can put a router like Envoy AI Gateway or LiteLLM in the traffic path and DeepInspect at the AI request boundary in front of it.

DeepInspect is a stateless proxy you deploy inside your own environment. It binds each routed HTTP LLM call to the natural-person or agent identity your application supplies, classifies the prompt content against the regulated categories your sector recognizes, applies per-route and per-role policy, and commits a signed per-decision audit record before the response returns, on a write path the application never holds. That produces identity-bound policy tied to your own identity provider, along with an independent audit record that lives on infrastructure you control. Book a demo today.