@ai-sdk/gateway 4.0.35 → 4.0.37

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @ai-sdk/gateway
 
+## 4.0.37
+
+### Patch Changes
+
+- bdd5e28: feat(provider/gateway): support `'vision'` (image input) in the `has` provider option
+
+## 4.0.36
+
+### Patch Changes
+
+- Updated dependencies [5fc7da5]
+- Updated dependencies [93b2acd]
+  - @ai-sdk/provider-utils@5.0.18
+
 ## 4.0.35
 
 ### Patch Changes

package/dist/index.d.ts

@@ -840,9 +840,9 @@ type GatewayProviderOptions = {
     disallowPromptTraining?: boolean;
     /**
      * Restrict routing to models that have all of the given capabilities.
-     * Currently supports `'implicit-caching'`.
+     * Currently supports `'implicit-caching'` and `'vision'` (image input).
      */
-    has?: Array<'implicit-caching'>;
+    has?: Array<'implicit-caching' | 'vision'>;
     /** Array of model slugs specifying fallback models to use in order. */
     models?: string[];
     /** Array of provider slugs that are the only ones allowed to be used. */

package/dist/index.js

@@ -2631,7 +2631,7 @@ async function getVercelRequestId() {
 }
 
 // src/version.ts
-var VERSION = true ? "4.0.35" : "0.0.0-test";
+var VERSION = true ? "4.0.37" : "0.0.0-test";
 
 // src/gateway-provider.ts
 var AI_GATEWAY_PROTOCOL_VERSION = "0.0.1";

package/docs/00-ai-gateway.mdx

@@ -1041,11 +1041,15 @@ The following gateway provider options are available:
 
   The unique identifier for the entity against which quota is tracked. Used for quota management and enforcement purposes.
 
-- **has** _Array<'implicit-caching'>_
+- **has** _Array<'implicit-caching' | 'vision'>_
 
-  Restricts routing to provider models that have all of the specified capabilities. Currently supports `'implicit-caching'`, which limits routing to models that perform automatic (implicit) prompt caching. Applies to both BYOK and system credentials, since the capability is a property of the model rather than the credential. If no provider model for the requested model satisfies the capabilities, the request fails. Unsupported values are rejected.
+  Restricts routing to provider models that have all of the specified capabilities. Applies to both BYOK and system credentials, since the capability is a property of the model rather than the credential. If no provider model for the requested model satisfies the capabilities, the request fails. Unsupported values are rejected.
 
-  Example: `has: ['implicit-caching']` will only route to models that support implicit caching.
+  Supported capabilities:
+  - `'implicit-caching'` — models that perform automatic (implicit) prompt caching.
+  - `'vision'` — models that accept image input.
+
+  Example: `has: ['implicit-caching']` will only route to models that support implicit caching. Example: `has: ['vision']` will only route to models that accept image input.
 
 - **providerTimeouts** _object_
 
@@ -1183,7 +1187,7 @@ const { text } = await generateText({
 
 #### Filtering by Model Capability
 
-Set `has` to restrict routing to provider models that have the specified capabilities. This applies to both BYOK and system credentials, since the capability is a property of the model rather than the credential. Currently `'implicit-caching'` is supported, which limits routing to models that perform automatic prompt caching. If no provider model for the requested model satisfies the capabilities, the request fails.
+Set `has` to restrict routing to provider models that have the specified capabilities. This applies to both BYOK and system credentials, since the capability is a property of the model rather than the credential. `'implicit-caching'` limits routing to models that perform automatic prompt caching, and `'vision'` limits routing to models that accept image input. If no provider model for the requested model satisfies the capabilities, the request fails.
 
 ```ts
 import type { GatewayProviderOptions } from '@ai-sdk/gateway';
@@ -1200,6 +1204,37 @@ const { text } = await generateText({
 });
 ```
 
+Use `'vision'` when the request sends image input, so the gateway only routes to
+provider models that can accept it:
+
+```ts
+import type { GatewayProviderOptions } from '@ai-sdk/gateway';
+import { generateText } from 'ai';
+import fs from 'node:fs';
+
+const { text } = await generateText({
+  model: 'anthropic/claude-sonnet-4.6',
+  messages: [
+    {
+      role: 'user',
+      content: [
+        { type: 'text', text: 'Describe the image in detail.' },
+        {
+          type: 'file',
+          mediaType: 'image/png',
+          data: fs.readFileSync('./data/comic-cat.png'),
+        },
+      ],
+    },
+  ],
+  providerOptions: {
+    gateway: {
+      has: ['vision'],
+    } satisfies GatewayProviderOptions,
+  },
+});
+```
+
 ### Provider-Specific Options
 
 When using provider-specific options through AI Gateway, use the actual provider name (e.g. `anthropic`, `openai`, not `gateway`) as the key:

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@ai-sdk/gateway",
   "private": false,
-  "version": "4.0.35",
+  "version": "4.0.37",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -32,7 +32,7 @@
   "dependencies": {
     "@vercel/oidc": "3.2.0",
     "@ai-sdk/provider": "4.0.4",
-    "@ai-sdk/provider-utils": "5.0.17"
+    "@ai-sdk/provider-utils": "5.0.18"
   },
   "devDependencies": {
     "@types/node": "22.19.19",

package/src/gateway-provider-options.ts

@@ -17,9 +17,9 @@ export type GatewayProviderOptions = {
 
   /**
    * Restrict routing to models that have all of the given capabilities.
-   * Currently supports `'implicit-caching'`.
+   * Currently supports `'implicit-caching'` and `'vision'` (image input).
    */
-  has?: Array<'implicit-caching'>;
+  has?: Array<'implicit-caching' | 'vision'>;
 
   /** Array of model slugs specifying fallback models to use in order. */
   models?: string[];