ai 7.0.104 → 7.0.105

package/docs/03-ai-sdk-core/32-evaluation.mdx

@@ -11,8 +11,8 @@ is one state, not a batch of unrelated inputs.
 
 This API and the evaluation model specification are experimental and may change
 in patch releases. Pass an evaluation model instance, resolve a model through a
-provider registry, or use a string ID with an evaluation-capable default provider.
-Evaluation does not fall back to Vercel AI Gateway.
+provider registry, or use a string ID. Strings resolve through Vercel AI Gateway
+unless you configure an evaluation-capable default provider.
 
 ```ts
 import { experimental_evaluate, type Experimental_EvaluationModel } from 'ai';
@@ -125,8 +125,26 @@ evaluation models.
 
 ### Default-provider strings
 
-To use strings directly, configure the default provider once at application
-startup:
+String IDs use Vercel AI Gateway by default. Configure Gateway authentication
+with `AI_GATEWAY_API_KEY` or Vercel OIDC, then pass a Gateway model ID:
+
+```ts
+import { experimental_evaluate } from 'ai';
+
+const result = await experimental_evaluate({
+  model: 'typesafe-ai/jev-latest',
+  state: 'I was charged twice. Please refund the extra charge.',
+  questions: {
+    refund: {
+      type: 'boolean',
+      instructions: 'Is the customer asking for a refund?',
+    },
+  },
+});
+```
+
+To resolve strings through your own provider or aliases, configure the default
+provider once at application startup:
 
 ```ts
 // Using the registry above, expose an alias through a custom provider:
@@ -152,9 +170,10 @@ also resolve through this global default. Prefer model instances in aliases to
 avoid resolution cycles. Global configuration affects other AI SDK functions
 too; avoid changing it per request in a shared process.
 
-Strings require an explicitly configured provider with an `evaluationModel`
-method. There is no assumed Gateway evaluation support. Missing providers throw
-`NoSuchProviderError`; missing models or evaluation capabilities throw
+An explicitly configured default provider must expose an `evaluationModel`
+method; Gateway is used only when no default provider is configured. Missing
+registry providers throw `NoSuchProviderError`; missing models or evaluation
+capabilities throw
 `NoSuchModelError` with `modelType: 'evaluationModel'`. Unsupported model versions
 throw `UnsupportedModelVersionError`, including models returned by registries.
 The stable `ProviderV4` and `ProviderRegistryProvider` interfaces are unchanged;

package/docs/03-ai-sdk-core/45-provider-management.mdx

@@ -473,8 +473,8 @@ This simplifies provider usage and makes it easier to switch between providers w
 
 Custom providers accept `evaluationModels` aliases, and registries expose
 `evaluationModel('provider:model')`. These methods return model instances for
-`experimental_evaluate`. An explicitly configured default provider with an
-`evaluationModel` method also enables direct string IDs; evaluation does not
-implicitly use Gateway. Registry middleware for language and image models does
-not apply to evaluation. See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
+`experimental_evaluate`. Direct string IDs use Gateway by default, or an
+explicitly configured default provider with an `evaluationModel` method. Registry
+middleware for language and image models does not apply to evaluation.
+See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
 for aliases, default-provider configuration, and capability differences.

package/docs/07-reference/01-ai-sdk-core/14-evaluate.mdx

@@ -14,15 +14,15 @@ state. See [Evaluation](/docs/ai-sdk-core/evaluation) for examples and semantics
 
 ## Parameters
 
-| Parameter         | Type                                              | Description                                                                                                                      |
-| ----------------- | ------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------- |
-| `model`           | `Experimental_EvaluationModel`                    | Required experimental v4 model instance or a string ID resolved by an explicitly configured evaluation-capable default provider. |
-| `state`           | `string \| object \| array`                       | Required JSON-compatible shared state.                                                                                           |
-| `questions`       | `Record<string, Experimental_EvaluationQuestion>` | Required nonempty question map.                                                                                                  |
-| `maxRetries`      | `number`                                          | Nonnegative integer; defaults to 2.                                                                                              |
-| `abortSignal`     | `AbortSignal`                                     | Cancels evaluation.                                                                                                              |
-| `headers`         | `Record<string, string>`                          | Additional HTTP headers.                                                                                                         |
-| `providerOptions` | `ProviderOptions`                                 | Provider-specific options.                                                                                                       |
+| Parameter         | Type                                              | Description                                                                                                                                 |
+| ----------------- | ------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------- |
+| `model`           | `Experimental_EvaluationModel`                    | Required experimental v4 model instance or a string ID resolved by Gateway or an explicitly configured evaluation-capable default provider. |
+| `state`           | `string \| object \| array`                       | Required JSON-compatible shared state.                                                                                                      |
+| `questions`       | `Record<string, Experimental_EvaluationQuestion>` | Required nonempty question map.                                                                                                             |
+| `maxRetries`      | `number`                                          | Nonnegative integer; defaults to 2.                                                                                                         |
+| `abortSignal`     | `AbortSignal`                                     | Cancels evaluation.                                                                                                                         |
+| `headers`         | `Record<string, string>`                          | Additional HTTP headers.                                                                                                                    |
+| `providerOptions` | `ProviderOptions`                                 | Provider-specific options.                                                                                                                  |
 
 ## Result
 

package/docs/07-reference/01-ai-sdk-core/40-provider-registry.mdx

@@ -312,6 +312,7 @@ retain experimental evaluation access.
 Unavailable evaluation capabilities or models throw `NoSuchModelError` with
 `modelType: 'evaluationModel'`; unknown registry providers throw
 `NoSuchProviderError`. These capabilities are structural extensions and are not
-added to the stable `ProviderV4` contract. Evaluation does not assume Gateway
-support. See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
+added to the stable `ProviderV4` contract. Direct evaluation string IDs default
+to Gateway when no default provider is configured.
+See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
 for runnable usage patterns.

package/docs/07-reference/01-ai-sdk-core/42-custom-provider.mdx

@@ -207,13 +207,15 @@ The `customProvider` function returns a `Provider` instance. It has the followin
 Pass `evaluationModels: Record<string, Experimental_EvaluationModel>` to define
 aliases for evaluation model instances or string IDs. The returned provider adds
 `evaluationModel(alias): Experimental_EvaluationModelV4`. String aliases resolve
-through an explicitly configured default provider with an `evaluationModel`
-method. Unknown aliases use the fallback provider's evaluation factory when
-available; model failures and unsupported questions do not trigger substitution.
+through Gateway by default, or an explicitly configured default provider with
+an `evaluationModel` method. Unknown aliases use the fallback provider's evaluation
+factory when available; model failures and unsupported questions do not trigger
+substitution.
 
 Unavailable evaluation capabilities or models throw `NoSuchModelError` with
 `modelType: 'evaluationModel'`; unknown registry providers throw
 `NoSuchProviderError`. These capabilities are structural extensions and are not
-added to the stable `ProviderV4` contract. Evaluation does not assume Gateway
-support. See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
+added to the stable `ProviderV4` contract. Direct evaluation string IDs default
+to Gateway when no default provider is configured.
+See [Evaluation](/docs/ai-sdk-core/evaluation#model-aliases-and-registries)
 for runnable usage patterns.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.104",
+  "version": "7.0.105",
   "type": "module",
   "description": "AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.",
   "license": "Apache-2.0",
@@ -42,7 +42,7 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.84",
+    "@ai-sdk/gateway": "4.0.85",
     "@ai-sdk/provider": "4.0.17",
     "@ai-sdk/provider-utils": "5.0.43"
   },

package/src/model/resolve-model.ts

@@ -222,10 +222,8 @@ export function resolveEvaluationModel(
 ): EvaluationModelV4 {
   if (typeof model === 'string') {
     // Use the original provider so experimental methods and their receiver survive.
-    // Evaluation does not default to Gateway.
-    const provider = globalThis.AI_SDK_DEFAULT_PROVIDER as
-      | EvaluationProvider
-      | undefined;
+    const provider = (globalThis.AI_SDK_DEFAULT_PROVIDER ??
+      gateway) as EvaluationProvider;
 
     if (typeof provider?.evaluationModel !== 'function') {
       throw new NoSuchModelError({