@ai-sdk/gateway 4.0.0-beta.111 → 4.0.0-beta.113

package/docs/00-ai-gateway.mdx

@@ -251,30 +251,52 @@ const model = gateway.experimental_realtime('openai/gpt-realtime-2');
 
 The Gateway normalizes realtime the same way it normalizes every other modality: your client speaks the [normalized AI SDK realtime protocol](/docs/ai-sdk-core/realtime) and the Gateway translates to and from the upstream provider server-side. This means the same client code works regardless of which provider backs the model.
 
-Gateway realtime v0 is server-side only. Calling `gateway.experimental_realtime()` in a browser throws an error. `getToken()` returns the Gateway auth token resolved by the provider (`apiKey`, `AI_GATEWAY_API_KEY`, or Vercel OIDC token), so do not expose it to browser clients.
+Realtime sessions run in the browser and require a short-lived Gateway client secret created on your server with `gateway.experimental_realtime.getToken()`. The method uses your Gateway credential (`apiKey`, `AI_GATEWAY_API_KEY`, or Vercel OIDC token) to mint a `vcst_` client secret and returns the WebSocket URL for the model.
 
-```ts
-import { gateway } from '@ai-sdk/gateway';
+```ts filename='app/api/realtime/setup/route.ts'
+import { gateway } from 'ai';
 
-// Server-side only. Do not return this token to browser clients.
-const token = await gateway.experimental_realtime.getToken({
-  model: 'openai/gpt-realtime-2',
-});
+export async function POST() {
+  const token = await gateway.experimental_realtime.getToken({
+    model: 'openai/gpt-realtime-2',
+    expiresAfterSeconds: 60 * 10,
+  });
+
+  return Response.json(token);
+}
 ```
 
-<Note>
-  Gateway realtime v0 does not mint a provider-style short-lived client secret.
-  Gateway-minted ephemeral secrets are planned as future work; browser support
-  should wait for that flow.
-</Note>
+Use the matching Gateway realtime model in the browser. Creating the model is
+safe in browser code; only `getToken()` is server-side.
+
+```tsx filename='app/realtime/page.tsx'
+'use client';
+
+import { experimental_useRealtime } from '@ai-sdk/react';
+import { gateway } from 'ai';
+
+export default function RealtimePage() {
+  const realtime = experimental_useRealtime({
+    model: gateway.experimental_realtime('openai/gpt-realtime-2'),
+    api: {
+      token: '/api/realtime/setup',
+    },
+  });
+
+  // ...
+}
+```
+
+Do not expose your Gateway API key or OIDC token to browser clients. Only return
+the short-lived setup response from `getToken()`.
 
 <Note>
-  The Gateway WebSocket route transports auth via the versioned
-  `Sec-WebSocket-Protocol` subprotocol and the model id via the `?ai-model-id=`
-  query - the WebSocket transport of the `Authorization` and `ai-model-id`
-  headers the HTTP routes use. Subprotocol values must fit the WebSocket token
-  grammar, and the complete `Sec-WebSocket-Protocol` header should stay compact
-  (under an 8 KiB safe header budget).
+  The Gateway WebSocket route transports the short-lived auth token via the
+  versioned `Sec-WebSocket-Protocol` subprotocol and the model id via the
+  `?ai-model-id=` query - the WebSocket transport of the `Authorization` and
+  `ai-model-id` headers the HTTP routes use. Subprotocol values must fit the
+  WebSocket token grammar, and the complete `Sec-WebSocket-Protocol` header
+  should stay compact (under an 8 KiB safe header budget).
 </Note>
 
 ### Provider Options
@@ -298,10 +320,10 @@ const sessionConfig = {
 The `GatewayProviderOptions` type is exported from `@ai-sdk/gateway` for stable client-facing fields. The type also accepts service-owned option keys so the Gateway service can add or change server-side options without requiring an SDK release for every schema change. Runtime validation is owned by the Gateway service.
 
 <Note>
-  Provider options are sent in the first `session.update` frame (after the
-  socket opens), so connect-time options such as `byok` and quota selection
-  require a Gateway that resolves them from that frame. Routing knobs like
-  `order` / `only` do not apply to realtime, where the Gateway selects the
+  Provider options are sent in the initial session update after the socket
+  opens, so connect-time options such as `byok` and quota selection require a
+  Gateway that resolves them from that update. Routing knobs like `order` /
+  `only` do not apply to realtime, where the Gateway selects the
   WebSocket-capable provider.
 </Note>
 

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@ai-sdk/gateway",
   "private": false,
-  "version": "4.0.0-beta.111",
+  "version": "4.0.0-beta.113",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -31,8 +31,8 @@
   },
   "dependencies": {
     "@vercel/oidc": "3.2.0",
-    "@ai-sdk/provider": "4.0.0-beta.19",
-    "@ai-sdk/provider-utils": "5.0.0-beta.49"
+    "@ai-sdk/provider": "4.0.0-beta.20",
+    "@ai-sdk/provider-utils": "5.0.0-beta.50"
   },
   "devDependencies": {
     "@types/node": "22.19.19",

package/src/gateway-language-model-settings.ts

@@ -165,6 +165,7 @@ export type GatewayModelId =
   | 'perplexity/sonar'
   | 'perplexity/sonar-pro'
   | 'perplexity/sonar-reasoning-pro'
+  | 'sakana/fugu-ultra'
   | 'stepfun/step-3.5-flash'
   | 'stepfun/step-3.7-flash'
   | 'xai/grok-4.1-fast-non-reasoning'

package/src/gateway-realtime-model-settings.ts

@@ -1 +1,6 @@
-export type GatewayRealtimeModelId = string & {};
+export type GatewayRealtimeModelId =
+  | 'openai/gpt-realtime-1.5'
+  | 'openai/gpt-realtime-2'
+  | 'openai/gpt-realtime-mini'
+  | 'xai/grok-voice-think-fast-1.0'
+  | (string & {});

package/src/gateway-speech-model-settings.ts

@@ -1 +1,4 @@
-export type GatewaySpeechModelId = string & {};
+export type GatewaySpeechModelId =
+  | 'openai/tts-1'
+  | 'openai/tts-1-hd'
+  | (string & {});

package/src/gateway-transcription-model-settings.ts

@@ -1 +1,5 @@
-export type GatewayTranscriptionModelId = string & {};
+export type GatewayTranscriptionModelId =
+  | 'openai/gpt-4o-mini-transcribe'
+  | 'openai/gpt-4o-transcribe'
+  | 'openai/whisper-1'
+  | (string & {});

package/src/gateway-video-model-settings.ts

@@ -7,8 +7,6 @@ export type GatewayVideoModelId =
   | 'alibaba/wan-v2.6-t2v'
   | 'bytedance/seedance-2.0'
   | 'bytedance/seedance-2.0-fast'
-  | 'bytedance/seedance-v1.0-lite-i2v'
-  | 'bytedance/seedance-v1.0-lite-t2v'
   | 'bytedance/seedance-v1.0-pro'
   | 'bytedance/seedance-v1.0-pro-fast'
   | 'bytedance/seedance-v1.5-pro'

package/src/gateway-video-model.ts

@@ -46,6 +46,7 @@ export class GatewayVideoModel implements Experimental_VideoModelV4 {
     duration,
     fps,
     seed,
+    generateAudio,
     image,
     providerOptions,
     headers,
@@ -81,6 +82,7 @@ export class GatewayVideoModel implements Experimental_VideoModelV4 {
           ...(duration && { duration }),
           ...(fps && { fps }),
           ...(seed && { seed }),
+          ...(generateAudio !== undefined && { generateAudio }),
           ...(providerOptions && { providerOptions }),
           ...(image && { image: maybeEncodeVideoFile(image) }),
         },