@ai-sdk/xai 4.0.0-beta.4 → 4.0.0-beta.41

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,316 @@
1
1
  # @ai-sdk/xai
2
2
 
3
+ ## 4.0.0-beta.41
4
+
5
+ ### Patch Changes
6
+
7
+ - Updated dependencies [f807e45]
8
+ - @ai-sdk/provider-utils@5.0.0-beta.24
9
+ - @ai-sdk/openai-compatible@3.0.0-beta.29
10
+
11
+ ## 4.0.0-beta.40
12
+
13
+ ### Patch Changes
14
+
15
+ - Updated dependencies [350ea38]
16
+ - @ai-sdk/provider-utils@5.0.0-beta.23
17
+ - @ai-sdk/openai-compatible@3.0.0-beta.28
18
+
19
+ ## 4.0.0-beta.39
20
+
21
+ ### Patch Changes
22
+
23
+ - Updated dependencies [083947b]
24
+ - @ai-sdk/provider-utils@5.0.0-beta.22
25
+ - @ai-sdk/openai-compatible@3.0.0-beta.27
26
+
27
+ ## 4.0.0-beta.38
28
+
29
+ ### Patch Changes
30
+
31
+ - Updated dependencies [add1126]
32
+ - @ai-sdk/provider-utils@5.0.0-beta.21
33
+ - @ai-sdk/openai-compatible@3.0.0-beta.26
34
+
35
+ ## 4.0.0-beta.37
36
+
37
+ ### Patch Changes
38
+
39
+ - 8d87577: fix(xai): support encrypted reasoning round-trip for ZDR
40
+
41
+ ## 4.0.0-beta.36
42
+
43
+ ### Patch Changes
44
+
45
+ - b3976a2: Add workflow serialization support to all provider models.
46
+
47
+ **`@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.
48
+
49
+ **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.
50
+
51
+ All provider model classes now include `WORKFLOW_SERIALIZE` and `WORKFLOW_DESERIALIZE` static methods, enabling them to cross workflow step boundaries without serialization errors.
52
+
53
+ - Updated dependencies [b3976a2]
54
+ - Updated dependencies [ff5eba1]
55
+ - @ai-sdk/provider-utils@5.0.0-beta.20
56
+ - @ai-sdk/openai-compatible@3.0.0-beta.25
57
+ - @ai-sdk/provider@4.0.0-beta.12
58
+
59
+ ## 4.0.0-beta.35
60
+
61
+ ### Major Changes
62
+
63
+ - ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only (`"type": "module"`). Consumers using `require()` must switch to ESM `import` syntax.
64
+
65
+ ### Patch Changes
66
+
67
+ - Updated dependencies [ef992f8]
68
+ - @ai-sdk/openai-compatible@3.0.0-beta.24
69
+ - @ai-sdk/provider@4.0.0-beta.11
70
+ - @ai-sdk/provider-utils@5.0.0-beta.19
71
+
72
+ ## 4.0.0-beta.34
73
+
74
+ ### Patch Changes
75
+
76
+ - 90e2d8a: chore: fix unused vars not being flagged by our lint tooling
77
+ - Updated dependencies [90e2d8a]
78
+ - @ai-sdk/openai-compatible@3.0.0-beta.23
79
+ - @ai-sdk/provider-utils@5.0.0-beta.18
80
+
81
+ ## 4.0.0-beta.33
82
+
83
+ ### Patch Changes
84
+
85
+ - Updated dependencies [3ae1786]
86
+ - @ai-sdk/provider-utils@5.0.0-beta.17
87
+ - @ai-sdk/openai-compatible@3.0.0-beta.22
88
+
89
+ ## 4.0.0-beta.32
90
+
91
+ ### Patch Changes
92
+
93
+ - Updated dependencies [176466a]
94
+ - @ai-sdk/provider@4.0.0-beta.10
95
+ - @ai-sdk/openai-compatible@3.0.0-beta.21
96
+ - @ai-sdk/provider-utils@5.0.0-beta.16
97
+
98
+ ## 4.0.0-beta.31
99
+
100
+ ### Patch Changes
101
+
102
+ - Updated dependencies [e311194]
103
+ - @ai-sdk/provider@4.0.0-beta.9
104
+ - @ai-sdk/openai-compatible@3.0.0-beta.20
105
+ - @ai-sdk/provider-utils@5.0.0-beta.15
106
+
107
+ ## 4.0.0-beta.30
108
+
109
+ ### Patch Changes
110
+
111
+ - e5bdc8d: fix (provider/xai): handle mid-stream error chunks
112
+
113
+ ## 4.0.0-beta.29
114
+
115
+ ### Patch Changes
116
+
117
+ - 813851f: fix (provider/xai): add response.incomplete and response.failed streaming event handling
118
+
119
+ ## 4.0.0-beta.28
120
+
121
+ ### Patch Changes
122
+
123
+ - Updated dependencies [34bd95d]
124
+ - Updated dependencies [008271d]
125
+ - @ai-sdk/provider@4.0.0-beta.8
126
+ - @ai-sdk/openai-compatible@3.0.0-beta.19
127
+ - @ai-sdk/provider-utils@5.0.0-beta.14
128
+
129
+ ## 4.0.0-beta.27
130
+
131
+ ### Patch Changes
132
+
133
+ - Updated dependencies [b0c2869]
134
+ - Updated dependencies [7e26e81]
135
+ - @ai-sdk/provider-utils@5.0.0-beta.13
136
+ - @ai-sdk/openai-compatible@3.0.0-beta.18
137
+
138
+ ## 4.0.0-beta.26
139
+
140
+ ### Patch Changes
141
+
142
+ - Updated dependencies [816ff67]
143
+ - @ai-sdk/openai-compatible@3.0.0-beta.17
144
+
145
+ ## 4.0.0-beta.25
146
+
147
+ ### Patch Changes
148
+
149
+ - Updated dependencies [46d1149]
150
+ - @ai-sdk/provider-utils@5.0.0-beta.12
151
+ - @ai-sdk/openai-compatible@3.0.0-beta.16
152
+
153
+ ## 4.0.0-beta.24
154
+
155
+ ### Patch Changes
156
+
157
+ - Updated dependencies [6fd51c0]
158
+ - @ai-sdk/provider-utils@5.0.0-beta.11
159
+ - @ai-sdk/provider@4.0.0-beta.7
160
+ - @ai-sdk/openai-compatible@3.0.0-beta.15
161
+
162
+ ## 4.0.0-beta.23
163
+
164
+ ### Patch Changes
165
+
166
+ - c29a26f: feat(provider): add support for provider references and uploading files as supported per provider
167
+ - Updated dependencies [c29a26f]
168
+ - @ai-sdk/openai-compatible@3.0.0-beta.14
169
+ - @ai-sdk/provider-utils@5.0.0-beta.10
170
+ - @ai-sdk/provider@4.0.0-beta.6
171
+
172
+ ## 4.0.0-beta.22
173
+
174
+ ### Patch Changes
175
+
176
+ - f51c95e: feat(provider/xai): add video extension and reference-to-video (R2V) support
177
+
178
+ ## 4.0.0-beta.21
179
+
180
+ ### Patch Changes
181
+
182
+ - 38fc777: Add AI Gateway hint to provider READMEs
183
+ - Updated dependencies [38fc777]
184
+ - @ai-sdk/openai-compatible@3.0.0-beta.13
185
+
186
+ ## 4.0.0-beta.20
187
+
188
+ ### Patch Changes
189
+
190
+ - Updated dependencies [2e17091]
191
+ - @ai-sdk/provider-utils@5.0.0-beta.9
192
+ - @ai-sdk/openai-compatible@3.0.0-beta.12
193
+
194
+ ## 4.0.0-beta.19
195
+
196
+ ### Patch Changes
197
+
198
+ - Updated dependencies [986c6fd]
199
+ - Updated dependencies [493295c]
200
+ - @ai-sdk/provider-utils@5.0.0-beta.8
201
+ - @ai-sdk/openai-compatible@3.0.0-beta.11
202
+
203
+ ## 4.0.0-beta.18
204
+
205
+ ### Patch Changes
206
+
207
+ - 9f20868: fix(provider/xai): correct finish reason for tool calls
208
+
209
+ ## 4.0.0-beta.17
210
+
211
+ ### Patch Changes
212
+
213
+ - Updated dependencies [1f509d4]
214
+ - @ai-sdk/provider-utils@5.0.0-beta.7
215
+ - @ai-sdk/provider@4.0.0-beta.5
216
+ - @ai-sdk/openai-compatible@3.0.0-beta.10
217
+
218
+ ## 4.0.0-beta.16
219
+
220
+ ### Patch Changes
221
+
222
+ - 4f91b5d: chore(provider/xai): update Grok 4.20 model IDs to their non-beta versions
223
+
224
+ ## 4.0.0-beta.15
225
+
226
+ ### Patch Changes
227
+
228
+ - 74d520f: feat: migrate providers to support new top-level `reasoning` parameter
229
+ - Updated dependencies [74d520f]
230
+ - @ai-sdk/openai-compatible@3.0.0-beta.9
231
+
232
+ ## 4.0.0-beta.14
233
+
234
+ ### Patch Changes
235
+
236
+ - Updated dependencies [3887c70]
237
+ - @ai-sdk/provider-utils@5.0.0-beta.6
238
+ - @ai-sdk/provider@4.0.0-beta.4
239
+ - @ai-sdk/openai-compatible@3.0.0-beta.8
240
+
241
+ ## 4.0.0-beta.13
242
+
243
+ ### Major Changes
244
+
245
+ - 776b617: feat(provider): adding new 'custom' content type
246
+
247
+ ### Patch Changes
248
+
249
+ - Updated dependencies [776b617]
250
+ - @ai-sdk/provider-utils@5.0.0-beta.5
251
+ - @ai-sdk/provider@4.0.0-beta.3
252
+ - @ai-sdk/openai-compatible@3.0.0-beta.7
253
+
254
+ ## 4.0.0-beta.12
255
+
256
+ ### Patch Changes
257
+
258
+ - d20829e: feat(provider/xai): add moderation error, and costInUsdTicks to video model
259
+ - Updated dependencies [61753c3]
260
+ - @ai-sdk/provider-utils@5.0.0-beta.4
261
+ - @ai-sdk/openai-compatible@3.0.0-beta.6
262
+
263
+ ## 4.0.0-beta.11
264
+
265
+ ### Patch Changes
266
+
267
+ - f7d4f01: feat(provider): add support for `reasoning-file` type for files that are part of reasoning
268
+ - Updated dependencies [f7d4f01]
269
+ - @ai-sdk/provider-utils@5.0.0-beta.3
270
+ - @ai-sdk/provider@4.0.0-beta.2
271
+ - @ai-sdk/openai-compatible@3.0.0-beta.5
272
+
273
+ ## 4.0.0-beta.10
274
+
275
+ ### Patch Changes
276
+
277
+ - Updated dependencies [5c2a5a2]
278
+ - @ai-sdk/provider@4.0.0-beta.1
279
+ - @ai-sdk/openai-compatible@3.0.0-beta.4
280
+ - @ai-sdk/provider-utils@5.0.0-beta.2
281
+
282
+ ## 4.0.0-beta.9
283
+
284
+ ### Patch Changes
285
+
286
+ - Updated dependencies [8f3e1da]
287
+ - @ai-sdk/openai-compatible@3.0.0-beta.3
288
+
289
+ ## 4.0.0-beta.8
290
+
291
+ ### Patch Changes
292
+
293
+ - 4799fa5: chore(provider/xai): update provider to use v4 types
294
+
295
+ ## 4.0.0-beta.7
296
+
297
+ ### Patch Changes
298
+
299
+ - 0f11f10: add reasoningSummary to responses API provider options
300
+ - 12115e9: fix reasoning text extraction from content in responses doGenerate
301
+
302
+ ## 4.0.0-beta.6
303
+
304
+ ### Major Changes
305
+
306
+ - f62681f: feat(provider/xai): make responses api the default
307
+
308
+ ## 4.0.0-beta.5
309
+
310
+ ### Patch Changes
311
+
312
+ - aa5a583: chore(provider/xai): remove obsolete Grok 2 models now that they are shut down in their API
313
+
3
314
  ## 4.0.0-beta.4
4
315
 
5
316
  ### Patch Changes
@@ -536,13 +847,13 @@
536
847
  Before
537
848
 
538
849
  ```ts
539
- model.textEmbeddingModel('my-model-id');
850
+ model.textEmbeddingModel("my-model-id");
540
851
  ```
541
852
 
542
853
  After
543
854
 
544
855
  ```ts
545
- model.embeddingModel('my-model-id');
856
+ model.embeddingModel("my-model-id");
546
857
  ```
547
858
 
548
859
  - 2625a04: feat(openai); update spec for mcp approval
@@ -800,13 +1111,13 @@
800
1111
  Before
801
1112
 
802
1113
  ```ts
803
- model.textEmbeddingModel('my-model-id');
1114
+ model.textEmbeddingModel("my-model-id");
804
1115
  ```
805
1116
 
806
1117
  After
807
1118
 
808
1119
  ```ts
809
- model.embeddingModel('my-model-id');
1120
+ model.embeddingModel("my-model-id");
810
1121
  ```
811
1122
 
812
1123
  - 8514146: add grok-4-1 model IDs
@@ -1349,7 +1660,7 @@
1349
1660
 
1350
1661
  ```js
1351
1662
  await generateImage({
1352
- model: luma.image('photon-flash-1', {
1663
+ model: luma.image("photon-flash-1", {
1353
1664
  maxImagesPerCall: 5,
1354
1665
  pollIntervalMillis: 500,
1355
1666
  }),
@@ -1362,7 +1673,7 @@
1362
1673
 
1363
1674
  ```js
1364
1675
  await generateImage({
1365
- model: luma.image('photon-flash-1'),
1676
+ model: luma.image("photon-flash-1"),
1366
1677
  prompt,
1367
1678
  n: 10,
1368
1679
  maxImagesPerCall: 5,
@@ -1678,7 +1989,7 @@
1678
1989
 
1679
1990
  ```js
1680
1991
  await generateImage({
1681
- model: luma.image('photon-flash-1', {
1992
+ model: luma.image("photon-flash-1", {
1682
1993
  maxImagesPerCall: 5,
1683
1994
  pollIntervalMillis: 500,
1684
1995
  }),
@@ -1691,7 +2002,7 @@
1691
2002
 
1692
2003
  ```js
1693
2004
  await generateImage({
1694
- model: luma.image('photon-flash-1'),
2005
+ model: luma.image("photon-flash-1"),
1695
2006
  prompt,
1696
2007
  n: 10,
1697
2008
  maxImagesPerCall: 5,
package/README.md CHANGED
@@ -3,6 +3,8 @@
3
3
  The **[xAI Grok provider](https://ai-sdk.dev/providers/ai-sdk-providers/xai)** for the [AI SDK](https://ai-sdk.dev/docs)
4
4
  contains language model support for the xAI chat and completion APIs.
5
5
 
6
+ > **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).
7
+
6
8
  ## Setup
7
9
 
8
10
  The xAI Grok provider is available in the `@ai-sdk/xai` module. You can install it with