@ai-sdk/anthropic 4.0.50 → 4.0.51

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @ai-sdk/anthropic
 
+## 4.0.51
+
+### Patch Changes
+
+- Updated dependencies [912fb01]
+  - @ai-sdk/provider@4.0.12
+  - @ai-sdk/provider-utils@5.0.38
+
 ## 4.0.50
 
 ### Patch Changes

package/dist/index.js

@@ -7573,7 +7573,7 @@ var AnthropicSkills = class {
 };
 
 // src/version.ts
-var VERSION = true ? "4.0.50" : "0.0.0-test";
+var VERSION = true ? "4.0.51" : "0.0.0-test";
 
 // src/anthropic-provider.ts
 var ANTHROPIC_API_URL = "https://api.anthropic.com";

package/docs/05-anthropic.mdx

@@ -144,65 +144,16 @@ The following optional provider options are available for Anthropic models:
   Optional. Metadata to include with the request. See the [Anthropic API documentation](https://platform.claude.com/docs/en/api/messages/create) for details.
   - `userId` _string_ - An external identifier for the end-user. Should be a UUID, hash, or other opaque identifier. Must not contain PII.
 
-### Text Batches
+### Batch
 
 <Note type="warning">
-  Text batch support is experimental and the API may change in patch releases.
+  Batch support is experimental and the API may change in patch releases.
 </Note>
 
 Anthropic language models support asynchronous text generation through the
 [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing).
-Use the experimental text batch APIs to start a batch, poll its status, and
-stream its results:
-
-```ts
-import { anthropic } from '@ai-sdk/anthropic';
-import {
-  experimental_getBatchResults as getBatchResults,
-  experimental_getBatchStatus as getBatchStatus,
-  experimental_startBatch as startBatch,
-} from 'ai';
-import { setTimeout } from 'node:timers/promises';
-
-const model = 'claude-haiku-4-5';
-
-const batch = await startBatch({
-  provider: anthropic,
-  requests: [
-    {
-      id: 'capital-france',
-      type: 'text',
-      model,
-      prompt: 'What is the capital of France?',
-    },
-    {
-      id: 'capital-germany',
-      type: 'text',
-      model: 'claude-sonnet-4-5',
-      prompt: 'What is the capital of Germany?',
-    },
-  ],
-});
-
-let status = batch.status;
-while (status === 'pending') {
-  await setTimeout(60_000);
-  ({ status } = await getBatchStatus({ provider: anthropic, batch }));
-}
-
-for await (const item of getBatchResults({ provider: anthropic, batch })) {
-  if (item.status === 'succeeded') {
-    console.log(item.id, item.text);
-  } else {
-    console.error(item.id, item.error);
-  }
-}
-```
-
-`startBatch` returns a serializable batch reference. Persist this reference
-to check the batch status or retrieve its results from another process. Results
-can arrive in a different order from the input requests, so match each result by
-its `id`.
+Pass the Anthropic provider to the AI SDK's [Batch](/docs/ai-sdk-core/batch)
+API for the complete workflow, including polling, persistence, and result handling.
 
 Each request specifies its `type` and `model`. Anthropic supports using
 different text models within the same batch.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/anthropic",
-  "version": "4.0.50",
+  "version": "4.0.51",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -35,8 +35,8 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/provider": "4.0.11",
-    "@ai-sdk/provider-utils": "5.0.37"
+    "@ai-sdk/provider": "4.0.12",
+    "@ai-sdk/provider-utils": "5.0.38"
   },
   "devDependencies": {
     "@ai-sdk/test-server": "2.0.1",