Vercel AI Gateway
API gatewayvercel-ai-gateway
Managed endpoint routing model calls across providers with failover, budgets, BYOK and request logs.
- Provider
- default
- Kind
- API gateway
- Category
- Edge
| property | type | values | required | kind default | this component |
|---|---|---|---|---|---|
| auth | enum | none | api-key | jwt | oauth2 | mtls | no | none | ▸ api-key |
| byok | boolean | — | no | false | inherited |
| concurrencyLimit | boolean | — | no | false | inherited |
| idempotencyKeys | boolean | — | no | false | inherited |
| instances | integer | — | no | — | inherited |
| keyTtlHours | integer | — | no | — | inherited |
| managed | boolean | — | no | false | ▸ true |
| modelFallbacks | boolean | — | no | false | inherited |
| protocol | enum | http | grpc | websocket | fix | ouch | no | http | ▸ http |
| providerAllowlist | boolean | — | no | false | inherited |
| rateLimiting | boolean | — | no | false | inherited |
| tls | boolean | — | no | true | ▸ true |
| zeroDataRetentionProviders | boolean | — | no | false | inherited |
Every rule whose selector covers this component's kind or its category. Whether a rule fires depends on the design: its properties, its edges and its groups.
sync-chain-too-deep
Every consecutive synchronous hop from this entry point spends part of the stated p95 latency budget, and the chain's failures multiply. More than three hops is a budget nobody is tracking.
- — all of these hold:
- — the design requirement `latency.p95Ms` has a value
- — the longest chain of synchronous calls starting at the node is more than 3 hops long
nodes:
- { id: "vercel-ai-gateway", component: "vercel-ai-gateway" }API Gatewayalibaba-api-gatewayAmazon API Gatewayaws-api-gatewayAWS AppSync GraphQL APIaws-appsyncAzure API Managementazure-api-managementAI Gatewaycloudflare-ai-gatewayCloudflare API Shieldcloudflare-api-shieldMCP Server Portalcloudflare-mcp-portalCloudflare Privacy Gatewaycloudflare-privacy-gatewayGeneric API gatewayapi-gatewayApache APISIXapisixApollo GraphOSapollo-graphosEasegresseasegressEmissary-ingressemissaryEnvoy Gatewayenvoy-gatewayGloo GatewayglooHasurahasuraHelicone AI Gatewayhelicone-gatewayHigresshigressKong GatewaykongKong AI Gatewaykong-ai-gatewayKong Konnectkong-konnectKrakenDkrakendLiteLLM ProxylitellmMartian GatewaymartianNot Diamondnot-diamondPortkey AI GatewayportkeyRequestyrequestySpring Cloud Gatewayspring-cloud-gatewayTyk GatewaytykUnifyunify-aiWSO2 API Managerwso2-api-managerZuulzuulApigeeapigeeAgent Gatewaygoogle-agent-gatewayAPI Gatewaygoogle-api-gatewayApigee hybridgoogle-apigee-hybridCloud Endpointsgoogle-cloud-endpointsFirebase Data Connectgoogle-firebase-data-connectIBM API Connectibm-api-connectOCI API Gatewayoci-api-gateway
# yaml-language-server: $schema=../../schema/component.schema.json # Vercel AI Gateway: managed endpoint that routes across providers with failover, budgets, BYOK and request # logs, callable from any infrastructure with an API key or OIDC on Vercel. Per "AI Gateway Security and # Compliance", the gateway itself keeps zero data retention by default, while routing only to ZDR providers # and the provider allowlist are opt-in; per "AI Gateway Model Fallbacks", backup models need a models list. schemaVersion: "1" type: "component" id: "vercel-ai-gateway" kind: "api-gateway" provider: "default" docs: "https://vercel.com/docs/ai-gateway/security-and-compliance" defaults: managed: true auth: "api-key" protocol: "http" tls: true properties: modelFallbacks: type: "boolean" default: false zeroDataRetentionProviders: type: "boolean" default: false providerAllowlist: type: "boolean" default: false byok: type: "boolean" default: false