@ai-sdk/xai 4.0.0-beta.4 → 4.0.0-beta.40

package/CHANGELOG.md

@@ -1,5 +1,308 @@
 # @ai-sdk/xai
 
+## 4.0.0-beta.40
+
+### Patch Changes
+
+- Updated dependencies [350ea38]
+  - @ai-sdk/provider-utils@5.0.0-beta.23
+  - @ai-sdk/openai-compatible@3.0.0-beta.28
+
+## 4.0.0-beta.39
+
+### Patch Changes
+
+- Updated dependencies [083947b]
+  - @ai-sdk/provider-utils@5.0.0-beta.22
+  - @ai-sdk/openai-compatible@3.0.0-beta.27
+
+## 4.0.0-beta.38
+
+### Patch Changes
+
+- Updated dependencies [add1126]
+  - @ai-sdk/provider-utils@5.0.0-beta.21
+  - @ai-sdk/openai-compatible@3.0.0-beta.26
+
+## 4.0.0-beta.37
+
+### Patch Changes
+
+- 8d87577: fix(xai): support encrypted reasoning round-trip for ZDR
+
+## 4.0.0-beta.36
+
+### Patch Changes
+
+- b3976a2: Add workflow serialization support to all provider models.
+
+  **`@ai-sdk/provider-utils`:** New `serializeModel()` helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.
+
+  **All providers:** `headers` is now optional in provider config types. This is non-breaking — existing code that passes `headers` continues to work. Custom provider implementations that construct model configs manually can now omit `headers`, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.
+
+  All provider model classes now include `WORKFLOW_SERIALIZE` and `WORKFLOW_DESERIALIZE` static methods, enabling them to cross workflow step boundaries without serialization errors.
+
+- Updated dependencies [b3976a2]
+- Updated dependencies [ff5eba1]
+  - @ai-sdk/provider-utils@5.0.0-beta.20
+  - @ai-sdk/openai-compatible@3.0.0-beta.25
+  - @ai-sdk/provider@4.0.0-beta.12
+
+## 4.0.0-beta.35
+
+### Major Changes
+
+- ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only (`"type": "module"`). Consumers using `require()` must switch to ESM `import` syntax.
+
+### Patch Changes
+
+- Updated dependencies [ef992f8]
+  - @ai-sdk/openai-compatible@3.0.0-beta.24
+  - @ai-sdk/provider@4.0.0-beta.11
+  - @ai-sdk/provider-utils@5.0.0-beta.19
+
+## 4.0.0-beta.34
+
+### Patch Changes
+
+- 90e2d8a: chore: fix unused vars not being flagged by our lint tooling
+- Updated dependencies [90e2d8a]
+  - @ai-sdk/openai-compatible@3.0.0-beta.23
+  - @ai-sdk/provider-utils@5.0.0-beta.18
+
+## 4.0.0-beta.33
+
+### Patch Changes
+
+- Updated dependencies [3ae1786]
+  - @ai-sdk/provider-utils@5.0.0-beta.17
+  - @ai-sdk/openai-compatible@3.0.0-beta.22
+
+## 4.0.0-beta.32
+
+### Patch Changes
+
+- Updated dependencies [176466a]
+  - @ai-sdk/provider@4.0.0-beta.10
+  - @ai-sdk/openai-compatible@3.0.0-beta.21
+  - @ai-sdk/provider-utils@5.0.0-beta.16
+
+## 4.0.0-beta.31
+
+### Patch Changes
+
+- Updated dependencies [e311194]
+  - @ai-sdk/provider@4.0.0-beta.9
+  - @ai-sdk/openai-compatible@3.0.0-beta.20
+  - @ai-sdk/provider-utils@5.0.0-beta.15
+
+## 4.0.0-beta.30
+
+### Patch Changes
+
+- e5bdc8d: fix (provider/xai): handle mid-stream error chunks
+
+## 4.0.0-beta.29
+
+### Patch Changes
+
+- 813851f: fix (provider/xai): add response.incomplete and response.failed streaming event handling
+
+## 4.0.0-beta.28
+
+### Patch Changes
+
+- Updated dependencies [34bd95d]
+- Updated dependencies [008271d]
+  - @ai-sdk/provider@4.0.0-beta.8
+  - @ai-sdk/openai-compatible@3.0.0-beta.19
+  - @ai-sdk/provider-utils@5.0.0-beta.14
+
+## 4.0.0-beta.27
+
+### Patch Changes
+
+- Updated dependencies [b0c2869]
+- Updated dependencies [7e26e81]
+  - @ai-sdk/provider-utils@5.0.0-beta.13
+  - @ai-sdk/openai-compatible@3.0.0-beta.18
+
+## 4.0.0-beta.26
+
+### Patch Changes
+
+- Updated dependencies [816ff67]
+  - @ai-sdk/openai-compatible@3.0.0-beta.17
+
+## 4.0.0-beta.25
+
+### Patch Changes
+
+- Updated dependencies [46d1149]
+  - @ai-sdk/provider-utils@5.0.0-beta.12
+  - @ai-sdk/openai-compatible@3.0.0-beta.16
+
+## 4.0.0-beta.24
+
+### Patch Changes
+
+- Updated dependencies [6fd51c0]
+  - @ai-sdk/provider-utils@5.0.0-beta.11
+  - @ai-sdk/provider@4.0.0-beta.7
+  - @ai-sdk/openai-compatible@3.0.0-beta.15
+
+## 4.0.0-beta.23
+
+### Patch Changes
+
+- c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
+- Updated dependencies [c29a26f]
+  - @ai-sdk/openai-compatible@3.0.0-beta.14
+  - @ai-sdk/provider-utils@5.0.0-beta.10
+  - @ai-sdk/provider@4.0.0-beta.6
+
+## 4.0.0-beta.22
+
+### Patch Changes
+
+- f51c95e: feat(provider/xai): add video extension and reference-to-video (R2V) support
+
+## 4.0.0-beta.21
+
+### Patch Changes
+
+- 38fc777: Add AI Gateway hint to provider READMEs
+- Updated dependencies [38fc777]
+  - @ai-sdk/openai-compatible@3.0.0-beta.13
+
+## 4.0.0-beta.20
+
+### Patch Changes
+
+- Updated dependencies [2e17091]
+  - @ai-sdk/provider-utils@5.0.0-beta.9
+  - @ai-sdk/openai-compatible@3.0.0-beta.12
+
+## 4.0.0-beta.19
+
+### Patch Changes
+
+- Updated dependencies [986c6fd]
+- Updated dependencies [493295c]
+  - @ai-sdk/provider-utils@5.0.0-beta.8
+  - @ai-sdk/openai-compatible@3.0.0-beta.11
+
+## 4.0.0-beta.18
+
+### Patch Changes
+
+- 9f20868: fix(provider/xai): correct finish reason for tool calls
+
+## 4.0.0-beta.17
+
+### Patch Changes
+
+- Updated dependencies [1f509d4]
+  - @ai-sdk/provider-utils@5.0.0-beta.7
+  - @ai-sdk/provider@4.0.0-beta.5
+  - @ai-sdk/openai-compatible@3.0.0-beta.10
+
+## 4.0.0-beta.16
+
+### Patch Changes
+
+- 4f91b5d: chore(provider/xai): update Grok 4.20 model IDs to their non-beta versions
+
+## 4.0.0-beta.15
+
+### Patch Changes
+
+- 74d520f: feat: migrate providers to support new top-level `reasoning` parameter
+- Updated dependencies [74d520f]
+  - @ai-sdk/openai-compatible@3.0.0-beta.9
+
+## 4.0.0-beta.14
+
+### Patch Changes
+
+- Updated dependencies [3887c70]
+  - @ai-sdk/provider-utils@5.0.0-beta.6
+  - @ai-sdk/provider@4.0.0-beta.4
+  - @ai-sdk/openai-compatible@3.0.0-beta.8
+
+## 4.0.0-beta.13
+
+### Major Changes
+
+- 776b617: feat(provider): adding new 'custom' content type
+
+### Patch Changes
+
+- Updated dependencies [776b617]
+  - @ai-sdk/provider-utils@5.0.0-beta.5
+  - @ai-sdk/provider@4.0.0-beta.3
+  - @ai-sdk/openai-compatible@3.0.0-beta.7
+
+## 4.0.0-beta.12
+
+### Patch Changes
+
+- d20829e: feat(provider/xai): add moderation error, and costInUsdTicks to video model
+- Updated dependencies [61753c3]
+  - @ai-sdk/provider-utils@5.0.0-beta.4
+  - @ai-sdk/openai-compatible@3.0.0-beta.6
+
+## 4.0.0-beta.11
+
+### Patch Changes
+
+- f7d4f01: feat(provider): add support for `reasoning-file` type for files that are part of reasoning
+- Updated dependencies [f7d4f01]
+  - @ai-sdk/provider-utils@5.0.0-beta.3
+  - @ai-sdk/provider@4.0.0-beta.2
+  - @ai-sdk/openai-compatible@3.0.0-beta.5
+
+## 4.0.0-beta.10
+
+### Patch Changes
+
+- Updated dependencies [5c2a5a2]
+  - @ai-sdk/provider@4.0.0-beta.1
+  - @ai-sdk/openai-compatible@3.0.0-beta.4
+  - @ai-sdk/provider-utils@5.0.0-beta.2
+
+## 4.0.0-beta.9
+
+### Patch Changes
+
+- Updated dependencies [8f3e1da]
+  - @ai-sdk/openai-compatible@3.0.0-beta.3
+
+## 4.0.0-beta.8
+
+### Patch Changes
+
+- 4799fa5: chore(provider/xai): update provider to use v4 types
+
+## 4.0.0-beta.7
+
+### Patch Changes
+
+- 0f11f10: add reasoningSummary to responses API provider options
+- 12115e9: fix reasoning text extraction from content in responses doGenerate
+
+## 4.0.0-beta.6
+
+### Major Changes
+
+- f62681f: feat(provider/xai): make responses api the default
+
+## 4.0.0-beta.5
+
+### Patch Changes
+
+- aa5a583: chore(provider/xai): remove obsolete Grok 2 models now that they are shut down in their API
+
 ## 4.0.0-beta.4
 
 ### Patch Changes
@@ -536,13 +839,13 @@
   Before
 
   ```ts
-  model.textEmbeddingModel('my-model-id');
+  model.textEmbeddingModel("my-model-id");
   ```
 
   After
 
   ```ts
-  model.embeddingModel('my-model-id');
+  model.embeddingModel("my-model-id");
   ```
 
 - 2625a04: feat(openai); update spec for mcp approval
@@ -800,13 +1103,13 @@
   Before
 
   ```ts
-  model.textEmbeddingModel('my-model-id');
+  model.textEmbeddingModel("my-model-id");
   ```
 
   After
 
   ```ts
-  model.embeddingModel('my-model-id');
+  model.embeddingModel("my-model-id");
   ```
 
 - 8514146: add grok-4-1 model IDs
@@ -1349,7 +1652,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1', {
+    model: luma.image("photon-flash-1", {
       maxImagesPerCall: 5,
       pollIntervalMillis: 500,
     }),
@@ -1362,7 +1665,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1'),
+    model: luma.image("photon-flash-1"),
     prompt,
     n: 10,
     maxImagesPerCall: 5,
@@ -1678,7 +1981,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1', {
+    model: luma.image("photon-flash-1", {
       maxImagesPerCall: 5,
       pollIntervalMillis: 500,
     }),
@@ -1691,7 +1994,7 @@
 
   ```js
   await generateImage({
-    model: luma.image('photon-flash-1'),
+    model: luma.image("photon-flash-1"),
     prompt,
     n: 10,
     maxImagesPerCall: 5,

package/README.md

@@ -3,6 +3,8 @@
 The **[xAI Grok provider](https://ai-sdk.dev/providers/ai-sdk-providers/xai)** for the [AI SDK](https://ai-sdk.dev/docs)
 contains language model support for the xAI chat and completion APIs.
 
+> **Deploying to Vercel?** With Vercel's AI Gateway you can access xAI (and hundreds of models from other providers) — no additional packages, API keys, or extra cost. [Get started with AI Gateway](https://vercel.com/ai-gateway).
+
 ## Setup
 
 The xAI Grok provider is available in the `@ai-sdk/xai` module. You can install it with