One read of Claude Developer Platformapi-20260925T153714Z
310 pages moved out of 637 read.
Pages moved
310
significant first
Pages read
637
in this capture
Captured
15:37 UTC
Corpus hash
850f99a0d461
corpus-hash
What this read moved
126-150 of 310, page 6 of 13This capture is too large to show at once. Changes 126-150 of 310 are below, significant first; the rest are on the following screens.
api/compliance/apps/sessions/remote Changed · +10 / -10 lines
from line 59
5959
6060 Maximum results (default: 100, max: 500)
6161
62 default: 100, maximum: 500, minimum: 1
62 default: 100, minimum: 1, maximum: 500
6363
6464- `organization_ids: optional array of string`
6565
from line 113
113113
114114 - `started_by_user: object or null`
115115
116 A user associated with a remote session.
116 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
117117
118118 - `id: string`
119119
from line 135
135135
136136 - `user: object or null`
137137
138 A user associated with a remote session.
138 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
139139
140140 - `id: string`
141141
from line 220
220220
221221 - `started_by_user: object or null`
222222
223 A user associated with a remote session.
223 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
224224
225225 - `id: string`
226226
from line 242
242242
243243 - `user: object or null`
244244
245 A user associated with a remote session.
245 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
246246
247247 - `id: string`
248248
from line 291
291291
292292 Maximum results (default: 100, max: 1000)
293293
294 default: 100, maximum: 1000, minimum: 1
294 default: 100, minimum: 1, maximum: 1000
295295
296296- `order: optional "asc" or "desc"`
297297
from line 311
311311
312312 Truncate each text item inside a tool result to at most this many bytes (cut on a code-point boundary). Pass `-1` to request the server maximum. `0` is not a valid value.
313313
314 default: 10000, maximum: 2147483647, minimum: -1
314 default: 10000, minimum: -1, maximum: 2147483647
315315
316316- `tool_use_input_max_bytes: optional number`
317317
318318 Truncate each tool-use input to at most this many bytes (cut on a code-point boundary so the result is valid UTF-8). Pass `-1` to request the server maximum. `0` is not a valid value.
319319
320 default: 10000, maximum: 2147483647, minimum: -1
320 default: 10000, minimum: -1, maximum: 2147483647
321321
322322#### Headers
323323
from line 479
479479
480480 - `started_by_user: object or null`
481481
482 A user associated with a remote session.
482 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
483483
484484 - `id: string`
485485
from line 501
501501
502502 - `user: object or null`
503503
504 A user associated with a remote session.
504 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
505505
506506 - `id: string`
507507
api/compliance/apps/sessions/remote/list Changed · +3 / -3 lines
from line 57
5757
5858 Maximum results (default: 100, max: 500)
5959
60 default: 100, maximum: 500, minimum: 1
60 default: 100, minimum: 1, maximum: 500
6161
6262- `organization_ids: optional array of string`
6363
from line 111
111111
112112 - `started_by_user: object or null`
113113
114 A user associated with a remote session.
114 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
115115
116116 - `id: string`
117117
from line 133
133133
134134 - `user: object or null`
135135
136 A user associated with a remote session.
136 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
137137
138138 - `id: string`
139139
api/compliance/apps/sessions/remote/messages Changed · +5 / -5 lines
from line 42
4242
4343 Maximum results (default: 100, max: 1000)
4444
45 default: 100, maximum: 1000, minimum: 1
45 default: 100, minimum: 1, maximum: 1000
4646
4747- `order: optional "asc" or "desc"`
4848
from line 62
6262
6363 Truncate each text item inside a tool result to at most this many bytes (cut on a code-point boundary). Pass `-1` to request the server maximum. `0` is not a valid value.
6464
65 default: 10000, maximum: 2147483647, minimum: -1
65 default: 10000, minimum: -1, maximum: 2147483647
6666
6767- `tool_use_input_max_bytes: optional number`
6868
6969 Truncate each tool-use input to at most this many bytes (cut on a code-point boundary so the result is valid UTF-8). Pass `-1` to request the server maximum. `0` is not a valid value.
7070
71 default: 10000, maximum: 2147483647, minimum: -1
71 default: 10000, minimum: -1, maximum: 2147483647
7272
7373### Headers
7474
from line 230
230230
231231 - `started_by_user: object or null`
232232
233 A user associated with a remote session.
233 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
234234
235235 - `id: string`
236236
from line 252
252252
253253 - `user: object or null`
254254
255 A user associated with a remote session.
255 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
256256
257257 - `id: string`
258258
api/compliance/apps/sessions/remote/messages/list Changed · +5 / -5 lines
from line 40
4040
4141 Maximum results (default: 100, max: 1000)
4242
43 default: 100, maximum: 1000, minimum: 1
43 default: 100, minimum: 1, maximum: 1000
4444
4545- `order: optional "asc" or "desc"`
4646
from line 60
6060
6161 Truncate each text item inside a tool result to at most this many bytes (cut on a code-point boundary). Pass `-1` to request the server maximum. `0` is not a valid value.
6262
63 default: 10000, maximum: 2147483647, minimum: -1
63 default: 10000, minimum: -1, maximum: 2147483647
6464
6565- `tool_use_input_max_bytes: optional number`
6666
6767 Truncate each tool-use input to at most this many bytes (cut on a code-point boundary so the result is valid UTF-8). Pass `-1` to request the server maximum. `0` is not a valid value.
6868
69 default: 10000, maximum: 2147483647, minimum: -1
69 default: 10000, minimum: -1, maximum: 2147483647
7070
7171## Headers
7272
from line 228
228228
229229 - `started_by_user: object or null`
230230
231 A user associated with a remote session.
231 The user who initiated an agent-owned session (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. For initiators no longer a member of an organization the key may read, the object is populated with `email_address` null.
232232
233233 - `id: string`
234234
from line 250
250250
251251 - `user: object or null`
252252
253 A user associated with a remote session.
253 The user who owns the session. Null for sessions owned by an automated agent rather than a user. At most one of `user` and `agent_id` is set. For users no longer a member of an organization the key may read, the object is populated with `email_address` null.
254254
255255 - `id: string`
256256
api/compliance/code Changed · +2 / -7 lines
from line 30
3030
3131 Maximum results (default: 20, max: 100)
3232
33 default: 20, maximum: 100, minimum: 1
33 default: 20, minimum: 1, maximum: 100
3434
3535- `organization_ids: optional array of string`
3636
from line 120
120120
121121 - `user: object or null`
122122
123 The user who owns a Code Artifact.
124
125 Fields that reference this type are null when the Artifact was
126 published by an agent session rather than a user account, when the
127 owner's account has been deleted, or when the owner is no longer a
128 member of an organization the key may read.
123 Artifact owner with email, or null if the Artifact was published by an agent session, the owner's account has been deleted, or the owner is no longer a member of an organization the key may read
129124
130125 - `id: string`
131126
api/compliance/code/artifacts Changed · +3 / -13 lines
from line 28
2828
2929 Maximum results (default: 20, max: 100)
3030
31 default: 20, maximum: 100, minimum: 1
31 default: 20, minimum: 1, maximum: 100
3232
3333- `organization_ids: optional array of string`
3434
from line 118
118118
119119 - `user: object or null`
120120
121 The user who owns a Code Artifact.
121 Artifact owner with email, or null if the Artifact was published by an agent session, the owner's account has been deleted, or the owner is no longer a member of an organization the key may read
122122
123 Fields that reference this type are null when the Artifact was
124 published by an agent session rather than a user account, when the
125 owner's account has been deleted, or when the owner is no longer a
126 member of an organization the key may read.
127
128123 - `id: string`
129124
130125 User identifier (tagged ID)
from line 328
333328
334329 - `user: object or null`
335330
336 The user who owns a Code Artifact.
337
338 Fields that reference this type are null when the Artifact was
339 published by an agent session rather than a user account, when the
340 owner's account has been deleted, or when the owner is no longer a
341 member of an organization the key may read.
331 Artifact owner with email, or null if the Artifact was published by an agent session, the owner's account has been deleted, or the owner is no longer a member of an organization the key may read
342332
343333 - `id: string`
344334
api/compliance/code/artifacts/list Changed · +2 / -7 lines
from line 26
2626
2727 Maximum results (default: 20, max: 100)
2828
29 default: 20, maximum: 100, minimum: 1
29 default: 20, minimum: 1, maximum: 100
3030
3131- `organization_ids: optional array of string`
3232
from line 116
116116
117117 - `user: object or null`
118118
119 The user who owns a Code Artifact.
120
121 Fields that reference this type are null when the Artifact was
122 published by an agent session rather than a user account, when the
123 owner's account has been deleted, or when the owner is no longer a
124 member of an organization the key may read.
119 Artifact owner with email, or null if the Artifact was published by an agent session, the owner's account has been deleted, or the owner is no longer a member of an organization the key may read
125120
126121 - `id: string`
127122
api/compliance/organizations Changed · +4 / -4 lines
from line 21
2121
2222 Maximum results (default: 1000, max: 1000)
2323
24 default: 1000, maximum: 1000, minimum: 1
24 default: 1000, minimum: 1, maximum: 1000
2525
2626- `page: optional string`
2727
from line 121
121121
122122 Maximum results (default: 500, max: 1000)
123123
124 default: 500, maximum: 1000, minimum: 1
124 default: 500, minimum: 1, maximum: 1000
125125
126126- `page: optional string`
127127
from line 235
235235
236236 Maximum results (default: 500, max: 1000)
237237
238 default: 500, maximum: 1000, minimum: 1
238 default: 500, minimum: 1, maximum: 1000
239239
240240- `page: optional string`
241241
from line 399
399399
400400 Maximum results (default: 500, max: 1000)
401401
402 default: 500, maximum: 1000, minimum: 1
402 default: 500, minimum: 1, maximum: 1000
403403
404404- `page: optional string`
405405
api/files Changed · +9 / -9 lines
from line 59
5959
6060 Original filename of the uploaded file.
6161
62 maxLength: 500, minLength: 1
62 minLength: 1, maxLength: 500
6363
6464 - `mime_type: string`
6565
6666 MIME type of the file.
6767
68 maxLength: 255, minLength: 1
68 minLength: 1, maxLength: 255
6969
7070 - `size_bytes: number`
7171
from line 128
128128
129129 Defaults to `20`. Ranges from `1` to `1000`.
130130
131 default: 20, maximum: 1000, minimum: 1
131 default: 20, minimum: 1, maximum: 1000
132132
133133- `page: optional string`
134134
from line 170
170170
171171 Original filename of the uploaded file.
172172
173 maxLength: 500, minLength: 1
173 minLength: 1, maxLength: 500
174174
175175 - `mime_type: string`
176176
177177 MIME type of the file.
178178
179 maxLength: 255, minLength: 1
179 minLength: 1, maxLength: 255
180180
181181 - `size_bytes: number`
182182
from line 302
302302
303303 Original filename of the uploaded file.
304304
305 maxLength: 500, minLength: 1
305 minLength: 1, maxLength: 500
306306
307307 - `mime_type: string`
308308
309309 MIME type of the file.
310310
311 maxLength: 255, minLength: 1
311 minLength: 1, maxLength: 255
312312
313313 - `size_bytes: number`
314314
from line 449
449449
450450 Original filename of the uploaded file.
451451
452 maxLength: 500, minLength: 1
452 minLength: 1, maxLength: 500
453453
454454 - `mime_type: string`
455455
456456 MIME type of the file.
457457
458 maxLength: 255, minLength: 1
458 minLength: 1, maxLength: 255
459459
460460 - `size_bytes: number`
461461
api/files/list Changed · +3 / -3 lines
from line 21
2121
2222 Defaults to `20`. Ranges from `1` to `1000`.
2323
24 default: 20, maximum: 1000, minimum: 1
24 default: 20, minimum: 1, maximum: 1000
2525
2626- `page: optional string`
2727
from line 63
6363
6464 Original filename of the uploaded file.
6565
66 maxLength: 500, minLength: 1
66 minLength: 1, maxLength: 500
6767
6868 - `mime_type: string`
6969
7070 MIME type of the file.
7171
72 maxLength: 255, minLength: 1
72 minLength: 1, maxLength: 255
7373
7474 - `size_bytes: number`
7575
api/messages Changed · +856 / -987 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 141
141141
142142 - `document_title: string or null`
143143
144 maxLength: 500, minLength: 1
144 minLength: 1, maxLength: 500
145145
146146 - `end_char_index: number`
147147
from line 161
161161
162162 - `document_title: string or null`
163163
164 maxLength: 500, minLength: 1
164 minLength: 1, maxLength: 500
165165
166166 - `end_page_number: number`
167167
from line 185
185185
186186 - `document_title: string or null`
187187
188 maxLength: 500, minLength: 1
188 minLength: 1, maxLength: 500
189189
190190 - `end_block_index: number`
191191
from line 209
209209
210210 - `title: string or null`
211211
212 maxLength: 512, minLength: 1
212 minLength: 1, maxLength: 512
213213
214214 - `url: string`
215215
from line 365
365365
366366 - `title: optional string or null`
367367
368 maxLength: 500, minLength: 1
368 minLength: 1, maxLength: 500
369369
370370 - `SearchResultBlockParam object`
371371
from line 429
429429
430430 - `name: string`
431431
432 maxLength: 200, minLength: 1
432 minLength: 1, maxLength: 200
433433
434434 - `cache_control: optional CacheControlEphemeral or null`
435435
from line 465
465465
466466 For a toolset member tool_use, the toolset family this member belongs to.
467467
468 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
468 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
469469
470470 - `ToolResultBlockParam object`
471471
from line 501
501501
502502 - `tool_name: string`
503503
504 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
504 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
505505
506506 - `cache_control: optional CacheControlEphemeral or null`
507507
from line 529
529529
530530 The caller-assigned identifier for this tab, unique within the inventory.
531531
532 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
532 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
533533
534534 - `title: string`
535535
from line 555
555555
556556 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
557557
558 maxItems: 200, minItems: 1
558 minItems: 1, maxItems: 200
559559
560560 - `BrowserStateChangeTabOpened object`
561561
from line 573
573573
574574 The `tab_id` of the opened tab, present in `tabs`.
575575
576 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
576 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
577577
578578 - `BrowserStateChangeDownloadStarted object`
579579
from line 585
585585
586586 The caller-assigned identifier for this download, stable across the state changes reporting it.
587587
588 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
588 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
589589
590590 - `url: string`
591591
from line 606
606606
607607 The caller-assigned identifier for this download, stable across the state changes reporting it.
608608
609 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
609 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
610610
611611 - `url: string`
612612
from line 618
618618
619619 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
620620
621 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
621 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
622622
623623 - `size_bytes: optional number or null`
624624
from line 636
636636
637637 The caller-assigned identifier for this download, stable across the state changes reporting it.
638638
639 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
639 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
640640
641641 - `url: string`
642642
from line 648
648648
649649 The failure or cancellation detail, when known.
650650
651 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
651 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
652652
653653 - `is_error: optional boolean`
654654
from line 656
656656
657657 For a toolset member tool_result, the toolset family of the paired tool_use.
658658
659 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
659 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
660660
661661 - `ServerToolUseBlockParam object`
662662
from line 1034
10341034
10351035 - `tool_name: string`
10361036
1037 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
1037 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
10381038
10391039 - `cache_control: optional CacheControlEphemeral or null`
10401040
from line 1075
10751075
10761076 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10771077
1078 - `string`
1079
10781080 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10791081
10801082 The model that will complete your prompt.
from line 1119
11171119
11181120 Powerful intelligence for long-running agents and coding
11191121
1120 - `"claude-mythos-preview"`
1121
1122 New class of intelligence, strongest in coding and cybersecurity
1123
11241122 - `"claude-opus-4-6"`
11251123
11261124 Powerful intelligence for long-running agents and coding
from line 1151
11531151
11541152 High-performance model for agents and coding
11551153
1156 - `string`
1154 - `"claude-mythos-preview"`
11571155
1156 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
1157
1158 New class of intelligence, strongest in coding and cybersecurity
1159
11581160- `cache_control: optional CacheControlEphemeral or null`
11591161
11601162 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 1191
11891191
11901192 Skill ID
11911193
1192 maxLength: 64, minLength: 1
1194 minLength: 1, maxLength: 64
11931195
11941196 - `version: optional string`
11951197
11961198 Skill version or 'latest' for most recent version
11971199
1198 maxLength: 64, minLength: 1
1200 minLength: 1, maxLength: 64
11991201
12001202 - `string`
12011203
12021204- `diagnostics: optional DiagnosticsParam or null`
12031205
1204 Request-level diagnostics. Currently carries the previous response
1205 id for prompt-cache divergence reporting.
1206 Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request.
12061207
12071208 - `previous_message_id: optional string or null`
12081209
from line 1233
12321233
12331234 - `effort: optional "low" or "medium" or "high" or 2 more or null`
12341235
1235 All possible effort levels.
1236 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
12361237
1238 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
1239
12371240 - `"low"`
12381241
12391242 - `"medium"`
from line 1485
14821485
14831486 This is how the tool will be called by the model and in `tool_use` blocks.
14841487
1485 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
1488 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
14861489
14871490 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
14881491
from line 1702
16991702
17001703 - `configs: optional BrowserToolsetConfigs or null`
17011704
1702 Per-member configuration for `browser_toolset_20260801`: one
1703 optional field per member tool, keyed by the member name — the same
1704 name the member's `tool_use` blocks carry. Every member is an
1705 accepted key, and a member's defaults apply wherever its key is
1706 absent. Unknown keys are rejected: the field set is this toolset
1707 version's complete member set.
1705 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
17081706
17091707 - `type: optional BrowserTypeConfig or null`
17101708
from line 2129
21312129
21322130 - `configs: optional ComputerToolsetConfigs or null`
21332131
2134 Per-member configuration for `computer_toolset_20260801`: one
2135 optional field per member tool, keyed by the member name — the same
2136 name the member's `tool_use` blocks carry. Every member is an
2137 accepted key, and a member's defaults apply wherever its key is
2138 absent. Unknown keys are rejected: the field set is this toolset
2139 version's complete member set.
2132 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
21402133
21412134 - `type: optional ComputerTypeConfig or null`
21422135
from line 2483
24902483
24912484 Maximum number of times the tool can be used in the API request.
24922485
2493 exclusiveMinimum: 0
2486 minimum: 1
24942487
24952488 - `strict: optional boolean`
24962489
from line 2499
25062499
25072500 The city of the user.
25082501
2509 maxLength: 255, minLength: 1
2502 minLength: 1, maxLength: 255
25102503
25112504 - `country: optional string or null`
25122505
25132506 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
25142507
2515 maxLength: 2, minLength: 2
2508 minLength: 2, maxLength: 2
25162509
25172510 - `region: optional string or null`
25182511
25192512 The region of the user.
25202513
2521 maxLength: 255, minLength: 1
2514 minLength: 1, maxLength: 255
25222515
25232516 - `timezone: optional string or null`
25242517
25252518 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
25262519
2527 maxLength: 255, minLength: 1
2520 minLength: 1, maxLength: 255
25282521
25292522 - `WebFetchTool20250910 object`
25302523
from line 2563
25702563
25712564 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
25722565
2573 exclusiveMinimum: 0
2566 minimum: 1
25742567
25752568 - `max_uses: optional number or null`
25762569
25772570 Maximum number of times the tool can be used in the API request.
25782571
2579 exclusiveMinimum: 0
2572 minimum: 1
25802573
25812574 - `strict: optional boolean`
25822575
from line 2577
25842577
25852578 - `url_sources: optional WebFetchURLSources or null`
25862579
2587 Which sources contribute to the set of URLs web fetch may fetch.
2580 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
25882581
2589 Each key is a tagged variant: `user_input` is `all` or `none`; the
2590 two tool filters are `all`, `none`, `only` (only the named tools'
2591 results) or `except` (every result but the named tools'). A named tool
2592 must be declared in this request's `tools[]`.
2593
25942582 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
25952583
25962584 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 2701
27132701
27142702 Maximum number of times the tool can be used in the API request.
27152703
2716 exclusiveMinimum: 0
2704 minimum: 1
27172705
27182706 - `strict: optional boolean`
27192707
from line 2755
27672755
27682756 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
27692757
2770 exclusiveMinimum: 0
2758 minimum: 1
27712759
27722760 - `max_uses: optional number or null`
27732761
27742762 Maximum number of times the tool can be used in the API request.
27752763
2776 exclusiveMinimum: 0
2764 minimum: 1
27772765
27782766 - `strict: optional boolean`
27792767
from line 2769
27812769
27822770 - `url_sources: optional WebFetchURLSources or null`
27832771
2784 Which sources contribute to the set of URLs web fetch may fetch.
2772 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
27852773
2786 Each key is a tagged variant: `user_input` is `all` or `none`; the
2787 two tool filters are `all`, `none`, `only` (only the named tools'
2788 results) or `except` (every result but the named tools'). A named tool
2789 must be declared in this request's `tools[]`.
2790
27912774 - `WebFetchTool20260309 object`
27922775
27932776 Web fetch tool with use_cache parameter for bypassing cached content.
from line 2817
28342817
28352818 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
28362819
2837 exclusiveMinimum: 0
2820 minimum: 1
28382821
28392822 - `max_uses: optional number or null`
28402823
28412824 Maximum number of times the tool can be used in the API request.
28422825
2843 exclusiveMinimum: 0
2826 minimum: 1
28442827
28452828 - `strict: optional boolean`
28462829
from line 2831
28482831
28492832 - `url_sources: optional WebFetchURLSources or null`
28502833
2851 Which sources contribute to the set of URLs web fetch may fetch.
2834 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28522835
2853 Each key is a tagged variant: `user_input` is `all` or `none`; the
2854 two tool filters are `all`, `none`, `only` (only the named tools'
2855 results) or `except` (every result but the named tools'). A named tool
2856 must be declared in this request's `tools[]`.
2857
28582836 - `use_cache: optional boolean`
28592837
28602838 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 2877
28992877
29002878 Maximum number of times the tool can be used in the API request.
29012879
2902 exclusiveMinimum: 0
2880 minimum: 1
29032881
29042882 - `response_inclusion: optional "full" or "excluded"`
29052883
from line 2939
29612939
29622940 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
29632941
2964 exclusiveMinimum: 0
2942 minimum: 1
29652943
29662944 - `max_uses: optional number or null`
29672945
29682946 Maximum number of times the tool can be used in the API request.
29692947
2970 exclusiveMinimum: 0
2948 minimum: 1
29712949
29722950 - `response_inclusion: optional "full" or "excluded"`
29732951
from line 2961
29832961
29842962 - `url_sources: optional WebFetchURLSources or null`
29852963
2986 Which sources contribute to the set of URLs web fetch may fetch.
2964 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
29872965
2988 Each key is a tagged variant: `user_input` is `all` or `none`; the
2989 two tool filters are `all`, `none`, `only` (only the named tools'
2990 results) or `except` (every result but the named tools'). A named tool
2991 must be declared in this request's `tools[]`.
2992
29932966 - `use_cache: optional boolean`
29942967
29952968 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 3049
30763049
30773050 Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
30783051
3079 maximum: 1, minimum: 0
3052 minimum: 0, maximum: 1
30803053
30813054- `top_k: optional number`
30823055
from line 3073
31003073
31013074 Recommended for advanced use cases only.
31023075
3103 maximum: 1, minimum: 0
3076 minimum: 0, maximum: 1
31043077
31053078### Returns
31063079
from line 3095
31223095
31233096 - `container: Container or null`
31243097
3125 Information about the container used in the request (for the code execution tool)
3098 Information about the container used in this request.
31263099
3100 This will be non-null if a container tool (e.g. code execution) was used.
3101
31273102 - `id: string`
31283103
31293104 Identifier for the container used in this request
from line 3125
31503125
31513126 Skill ID
31523127
3153 maxLength: 64, minLength: 1
3128 minLength: 1, maxLength: 64
31543129
31553130 - `version: string`
31563131
31573132 The resolved version: a skill version ID for custom skills.
31583133
3159 maxLength: 64, minLength: 1
3134 minLength: 1, maxLength: 64
31603135
31613136 - `content: array of ContentBlock`
31623137
from line 3304
33293304
33303305 - `text: string`
33313306
3332 minLength: 0
3333
33343307 - `ThinkingBlock object`
33353308
33363309 - `type: "thinking"`
from line 3384
34113384
34123385 For a toolset member tool_use, the toolset family.
34133386
3414 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
3387 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
34153388
34163389 - `ServerToolUseBlock object`
34173390
from line 3832
38593832
38603833 - `tool_name: string`
38613834
3862 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
3835 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
38633836
38643837 - `tool_use_id: string`
38653838
from line 3850
38773850
38783851 - `diagnostics: Diagnostics or null`
38793852
3880 Request-level diagnostics: why the prompt cache could not fully reuse
3881 the prefix of the request named by `diagnostics.previous_message_id`.
3853 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
38823854
38833855 - `cache_miss_reason: CacheMissReason or null`
38843856
from line 3914
39423914
39433915 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
39443916
3917 - `string`
3918
39453919 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
39463920
39473921 The model that will complete your prompt.
from line 3958
39843958
39853959 Powerful intelligence for long-running agents and coding
39863960
3987 - `"claude-mythos-preview"`
3988
3989 New class of intelligence, strongest in coding and cybersecurity
3990
39913961 - `"claude-opus-4-6"`
39923962
39933963 Powerful intelligence for long-running agents and coding
from line 3990
40203990
40213991 High-performance model for agents and coding
40223992
4023 - `string`
3993 - `"claude-mythos-preview"`
40243994
3995 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
3996
3997 New class of intelligence, strongest in coding and cybersecurity
3998
40253999 - `role: "assistant"`
40264000
40274001 Conversational role of the generated message.
from line 4006
40324006
40334007 - `stop_details: RefusalStopDetails or null`
40344008
4035 Structured information about a refusal.
4009 Structured information about why model output stopped.
40364010
4011 This is `null` when the `stop_reason` has no additional detail to report.
4012
40374013 - `type: "refusal"`
40384014
40394015 default: refusal
from line 4016
40404016
40414017 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
40424018
4043 The policy category that triggered a refusal.
4019 The policy category that triggered the refusal.
40444020
4021 `null` when the refusal doesn't map to a named category.
4022
40454023 - `"cyber"`
40464024
40474025 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
from line 4206
42284206
42294207 - `container: Container or null`
42304208
4231 Information about the container used in the request (for the code execution tool)
4209 Information about the container used in this request.
42324210
4211 This will be non-null if a container tool (e.g. code execution) was used.
4212
42334213 - `stop_details: RefusalStopDetails or null`
42344214
4235 Structured information about a refusal.
4215 Structured information about why model output stopped.
42364216
4217 This is `null` when the `stop_reason` has no additional detail to report.
4218
42374219 - `stop_reason: StopReason or null`
42384220
42394221 - `stop_sequence: string or null`
from line 4624
46424624
46434625 - `document_title: string or null`
46444626
4645 maxLength: 500, minLength: 1
4627 minLength: 1, maxLength: 500
46464628
46474629 - `end_char_index: number`
46484630
from line 4644
46624644
46634645 - `document_title: string or null`
46644646
4665 maxLength: 500, minLength: 1
4647 minLength: 1, maxLength: 500
46664648
46674649 - `end_page_number: number`
46684650
from line 4668
46864668
46874669 - `document_title: string or null`
46884670
4689 maxLength: 500, minLength: 1
4671 minLength: 1, maxLength: 500
46904672
46914673 - `end_block_index: number`
46924674
from line 4692
47104692
47114693 - `title: string or null`
47124694
4713 maxLength: 512, minLength: 1
4695 minLength: 1, maxLength: 512
47144696
47154697 - `url: string`
47164698
from line 4848
48664848
48674849 - `title: optional string or null`
48684850
4869 maxLength: 500, minLength: 1
4851 minLength: 1, maxLength: 500
48704852
48714853 - `SearchResultBlockParam object`
48724854
from line 4912
49304912
49314913 - `name: string`
49324914
4933 maxLength: 200, minLength: 1
4915 minLength: 1, maxLength: 200
49344916
49354917 - `cache_control: optional CacheControlEphemeral or null`
49364918
from line 4948
49664948
49674949 For a toolset member tool_use, the toolset family this member belongs to.
49684950
4969 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
4951 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
49704952
49714953 - `ToolResultBlockParam object`
49724954
from line 4984
50024984
50034985 - `tool_name: string`
50044986
5005 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
4987 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
50064988
50074989 - `cache_control: optional CacheControlEphemeral or null`
50084990
from line 5012
50305012
50315013 The caller-assigned identifier for this tab, unique within the inventory.
50325014
5033 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
5015 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
50345016
50355017 - `title: string`
50365018
from line 5038
50565038
50575039 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
50585040
5059 maxItems: 200, minItems: 1
5041 minItems: 1, maxItems: 200
50605042
50615043 - `BrowserStateChangeTabOpened object`
50625044
from line 5056
50745056
50755057 The `tab_id` of the opened tab, present in `tabs`.
50765058
5077 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
5059 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
50785060
50795061 - `BrowserStateChangeDownloadStarted object`
50805062
from line 5068
50865068
50875069 The caller-assigned identifier for this download, stable across the state changes reporting it.
50885070
5089 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
5071 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
50905072
50915073 - `url: string`
50925074
from line 5089
51075089
51085090 The caller-assigned identifier for this download, stable across the state changes reporting it.
51095091
5110 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
5092 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
51115093
51125094 - `url: string`
51135095
from line 5101
51195101
51205102 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
51215103
5122 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
5104 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
51235105
51245106 - `size_bytes: optional number or null`
51255107
from line 5119
51375119
51385120 The caller-assigned identifier for this download, stable across the state changes reporting it.
51395121
5140 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
5122 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
51415123
51425124 - `url: string`
51435125
from line 5131
51495131
51505132 The failure or cancellation detail, when known.
51515133
5152 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
5134 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
51535135
51545136 - `is_error: optional boolean`
51555137
from line 5139
51575139
51585140 For a toolset member tool_result, the toolset family of the paired tool_use.
51595141
5160 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
5142 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
51615143
51625144 - `ServerToolUseBlockParam object`
51635145
from line 5517
55355517
55365518 - `tool_name: string`
55375519
5538 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
5520 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
55395521
55405522 - `cache_control: optional CacheControlEphemeral or null`
55415523
from line 5558
55765558
55775559 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
55785560
5561 - `string`
5562
55795563 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
55805564
55815565 The model that will complete your prompt.
from line 5602
56185602
56195603 Powerful intelligence for long-running agents and coding
56205604
5621 - `"claude-mythos-preview"`
5622
5623 New class of intelligence, strongest in coding and cybersecurity
5624
56255605 - `"claude-opus-4-6"`
56265606
56275607 Powerful intelligence for long-running agents and coding
from line 5634
56545634
56555635 High-performance model for agents and coding
56565636
5657 - `string`
5637 - `"claude-mythos-preview"`
56585638
5639 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
5640
5641 New class of intelligence, strongest in coding and cybersecurity
5642
56595643- `cache_control: optional CacheControlEphemeral or null`
56605644
56615645 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 5650
56665650
56675651 - `effort: optional "low" or "medium" or "high" or 2 more or null`
56685652
5669 All possible effort levels.
5653 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
56705654
5655 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
5656
56715657 - `"low"`
56725658
56735659 - `"medium"`
from line 5878
58925878
58935879 This is how the tool will be called by the model and in `tool_use` blocks.
58945880
5895 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
5881 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
58965882
58975883 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
58985884
from line 6095
61096095
61106096 - `configs: optional BrowserToolsetConfigs or null`
61116097
6112 Per-member configuration for `browser_toolset_20260801`: one
6113 optional field per member tool, keyed by the member name — the same
6114 name the member's `tool_use` blocks carry. Every member is an
6115 accepted key, and a member's defaults apply wherever its key is
6116 absent. Unknown keys are rejected: the field set is this toolset
6117 version's complete member set.
6098 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
61186099
61196100 - `type: optional BrowserTypeConfig or null`
61206101
from line 6522
65416522
65426523 - `configs: optional ComputerToolsetConfigs or null`
65436524
6544 Per-member configuration for `computer_toolset_20260801`: one
6545 optional field per member tool, keyed by the member name — the same
6546 name the member's `tool_use` blocks carry. Every member is an
6547 accepted key, and a member's defaults apply wherever its key is
6548 absent. Unknown keys are rejected: the field set is this toolset
6549 version's complete member set.
6525 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
65506526
65516527 - `type: optional ComputerTypeConfig or null`
65526528
from line 6876
69006876
69016877 Maximum number of times the tool can be used in the API request.
69026878
6903 exclusiveMinimum: 0
6879 minimum: 1
69046880
69056881 - `strict: optional boolean`
69066882
from line 6892
69166892
69176893 The city of the user.
69186894
6919 maxLength: 255, minLength: 1
6895 minLength: 1, maxLength: 255
69206896
69216897 - `country: optional string or null`
69226898
69236899 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
69246900
6925 maxLength: 2, minLength: 2
6901 minLength: 2, maxLength: 2
69266902
69276903 - `region: optional string or null`
69286904
69296905 The region of the user.
69306906
6931 maxLength: 255, minLength: 1
6907 minLength: 1, maxLength: 255
69326908
69336909 - `timezone: optional string or null`
69346910
69356911 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
69366912
6937 maxLength: 255, minLength: 1
6913 minLength: 1, maxLength: 255
69386914
69396915 - `WebFetchTool20250910 object`
69406916
from line 6956
69806956
69816957 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
69826958
6983 exclusiveMinimum: 0
6959 minimum: 1
69846960
69856961 - `max_uses: optional number or null`
69866962
69876963 Maximum number of times the tool can be used in the API request.
69886964
6989 exclusiveMinimum: 0
6965 minimum: 1
69906966
69916967 - `strict: optional boolean`
69926968
from line 6970
69946970
69956971 - `url_sources: optional WebFetchURLSources or null`
69966972
6997 Which sources contribute to the set of URLs web fetch may fetch.
6973 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
69986974
6999 Each key is a tagged variant: `user_input` is `all` or `none`; the
7000 two tool filters are `all`, `none`, `only` (only the named tools'
7001 results) or `except` (every result but the named tools'). A named tool
7002 must be declared in this request's `tools[]`.
7003
70046975 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
70056976
70066977 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 7094
71237094
71247095 Maximum number of times the tool can be used in the API request.
71257096
7126 exclusiveMinimum: 0
7097 minimum: 1
71277098
71287099 - `strict: optional boolean`
71297100
from line 7148
71777148
71787149 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
71797150
7180 exclusiveMinimum: 0
7151 minimum: 1
71817152
71827153 - `max_uses: optional number or null`
71837154
71847155 Maximum number of times the tool can be used in the API request.
71857156
7186 exclusiveMinimum: 0
7157 minimum: 1
71877158
71887159 - `strict: optional boolean`
71897160
from line 7162
71917162
71927163 - `url_sources: optional WebFetchURLSources or null`
71937164
7194 Which sources contribute to the set of URLs web fetch may fetch.
7165 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
71957166
7196 Each key is a tagged variant: `user_input` is `all` or `none`; the
7197 two tool filters are `all`, `none`, `only` (only the named tools'
7198 results) or `except` (every result but the named tools'). A named tool
7199 must be declared in this request's `tools[]`.
7200
72017167 - `WebFetchTool20260309 object`
72027168
72037169 Web fetch tool with use_cache parameter for bypassing cached content.
from line 7210
72447210
72457211 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
72467212
7247 exclusiveMinimum: 0
7213 minimum: 1
72487214
72497215 - `max_uses: optional number or null`
72507216
72517217 Maximum number of times the tool can be used in the API request.
72527218
7253 exclusiveMinimum: 0
7219 minimum: 1
72547220
72557221 - `strict: optional boolean`
72567222
from line 7224
72587224
72597225 - `url_sources: optional WebFetchURLSources or null`
72607226
7261 Which sources contribute to the set of URLs web fetch may fetch.
7227 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
72627228
7263 Each key is a tagged variant: `user_input` is `all` or `none`; the
7264 two tool filters are `all`, `none`, `only` (only the named tools'
7265 results) or `except` (every result but the named tools'). A named tool
7266 must be declared in this request's `tools[]`.
7267
72687229 - `use_cache: optional boolean`
72697230
72707231 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 7270
73097270
73107271 Maximum number of times the tool can be used in the API request.
73117272
7312 exclusiveMinimum: 0
7273 minimum: 1
73137274
73147275 - `response_inclusion: optional "full" or "excluded"`
73157276
from line 7332
73717332
73727333 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
73737334
7374 exclusiveMinimum: 0
7335 minimum: 1
73757336
73767337 - `max_uses: optional number or null`
73777338
73787339 Maximum number of times the tool can be used in the API request.
73797340
7380 exclusiveMinimum: 0
7341 minimum: 1
73817342
73827343 - `response_inclusion: optional "full" or "excluded"`
73837344
from line 7354
73937354
73947355 - `url_sources: optional WebFetchURLSources or null`
73957356
7396 Which sources contribute to the set of URLs web fetch may fetch.
7357 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
73977358
7398 Each key is a tagged variant: `user_input` is `all` or `none`; the
7399 two tool filters are `all`, `none`, `only` (only the named tools'
7400 results) or `except` (every result but the named tools'). A named tool
7401 must be declared in this request's `tools[]`.
7402
74037359 - `use_cache: optional boolean`
74047360
74057361 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 8139
81838139
81848140 The caller-assigned identifier for this tab, unique within the inventory.
81858141
8186 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8142 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
81878143
81888144 - `title: string`
81898145
from line 8182
82268182
82278183 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
82288184
8229 maxItems: 200, minItems: 1
8185 minItems: 1, maxItems: 200
82308186
82318187 - `BrowserStateChangeTabOpened object`
82328188
from line 8200
82448200
82458201 The `tab_id` of the opened tab, present in `tabs`.
82468202
8247 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8203 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
82488204
82498205 - `BrowserStateChangeDownloadStarted object`
82508206
from line 8212
82568212
82578213 The caller-assigned identifier for this download, stable across the state changes reporting it.
82588214
8259 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8215 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
82608216
82618217 - `url: string`
82628218
from line 8233
82778233
82788234 The caller-assigned identifier for this download, stable across the state changes reporting it.
82798235
8280 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8236 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
82818237
82828238 - `url: string`
82838239
from line 8245
82898245
82908246 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
82918247
8292 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
8248 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
82938249
82948250 - `size_bytes: optional number or null`
82958251
from line 8263
83078263
83088264 The caller-assigned identifier for this download, stable across the state changes reporting it.
83098265
8310 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8266 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83118267
83128268 - `url: string`
83138269
from line 8275
83198275
83208276 The failure or cancellation detail, when known.
83218277
8322 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
8278 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83238279
83248280### Browser State Change
83258281
from line 8297
83418297
83428298 The `tab_id` of the opened tab, present in `tabs`.
83438299
8344 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8300 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83458301
83468302 - `BrowserStateChangeDownloadStarted object`
83478303
from line 8309
83538309
83548310 The caller-assigned identifier for this download, stable across the state changes reporting it.
83558311
8356 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8312 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83578313
83588314 - `url: string`
83598315
from line 8330
83748330
83758331 The caller-assigned identifier for this download, stable across the state changes reporting it.
83768332
8377 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8333 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83788334
83798335 - `url: string`
83808336
from line 8342
83868342
83878343 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
83888344
8389 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
8345 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
83908346
83918347 - `size_bytes: optional number or null`
83928348
from line 8360
84048360
84058361 The caller-assigned identifier for this download, stable across the state changes reporting it.
84068362
8407 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8363 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
84088364
8409
8365 - `url: string`
8366
8367 The final post-redirect URL the download was served from.
8368
8369 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8370
8371 - `error: optional string or null`
8372
8373 The failure or cancellation detail, when known.
8374
8375 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8376
8377### Browser State Change Download Completed
8378
8379- `BrowserStateChangeDownloadCompleted object`
8380
8381 A file download that finished during this call, reported with the
8382 same `download_id` as its `download_started` — or without a prior
8383 `download_started`, when the download finished during the call that
8384 started it (at most one state change per `download_id` per result).
8385
8386 - `type: "download_completed"`
8387
8388 - `download_id: string`
8389
8390 The caller-assigned identifier for this download, stable across the state changes reporting it.
8391
8392 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8393
8394 - `url: string`
8395
8396 The final post-redirect URL the download was served from.
8397
8398 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8399
8400 - `path: optional string or null`
8401
8402 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
8403
8404 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
8405
8406 - `size_bytes: optional number or null`
8407
8408 The completed download's size.
8409
8410 minimum: 0
8411
8412### Browser State Change Download Failed
8413
8414- `BrowserStateChangeDownloadFailed object`
8415
8416 A file download that failed — or was cancelled — during this call.
8417
8418 - `type: "download_failed"`
8419
8420 - `download_id: string`
8421
8422 The caller-assigned identifier for this download, stable across the state changes reporting it.
8423
8424 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x
api/messages/batches Changed · +326 / -333 lines
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 33
3333
3434 List of requests for prompt completion. Each is an individual request to create a Message.
3535
36 maxItems: 100000, minItems: 1
36 minItems: 1, maxItems: 100000
3737
3838 - `custom_id: string`
3939
from line 41
4141
4242 Must be unique for each request within the Message Batch.
4343
44 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,64}$
44 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]{1,64}$
4545
4646 - `params: object`
4747
from line 161
161161
162162 - `document_title: string or null`
163163
164 maxLength: 500, minLength: 1
164 minLength: 1, maxLength: 500
165165
166166 - `end_char_index: number`
167167
from line 181
181181
182182 - `document_title: string or null`
183183
184 maxLength: 500, minLength: 1
184 minLength: 1, maxLength: 500
185185
186186 - `end_page_number: number`
187187
from line 205
205205
206206 - `document_title: string or null`
207207
208 maxLength: 500, minLength: 1
208 minLength: 1, maxLength: 500
209209
210210 - `end_block_index: number`
211211
from line 229
229229
230230 - `title: string or null`
231231
232 maxLength: 512, minLength: 1
232 minLength: 1, maxLength: 512
233233
234234 - `url: string`
235235
from line 385
385385
386386 - `title: optional string or null`
387387
388 maxLength: 500, minLength: 1
388 minLength: 1, maxLength: 500
389389
390390 - `SearchResultBlockParam object`
391391
from line 449
449449
450450 - `name: string`
451451
452 maxLength: 200, minLength: 1
452 minLength: 1, maxLength: 200
453453
454454 - `cache_control: optional CacheControlEphemeral or null`
455455
from line 485
485485
486486 For a toolset member tool_use, the toolset family this member belongs to.
487487
488 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
488 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
489489
490490 - `ToolResultBlockParam object`
491491
from line 521
521521
522522 - `tool_name: string`
523523
524 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
524 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
525525
526526 - `cache_control: optional CacheControlEphemeral or null`
527527
from line 549
549549
550550 The caller-assigned identifier for this tab, unique within the inventory.
551551
552 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
552 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
553553
554554 - `title: string`
555555
from line 575
575575
576576 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
577577
578 maxItems: 200, minItems: 1
578 minItems: 1, maxItems: 200
579579
580580 - `BrowserStateChangeTabOpened object`
581581
from line 593
593593
594594 The `tab_id` of the opened tab, present in `tabs`.
595595
596 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
596 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
597597
598598 - `BrowserStateChangeDownloadStarted object`
599599
from line 605
605605
606606 The caller-assigned identifier for this download, stable across the state changes reporting it.
607607
608 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
608 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
609609
610610 - `url: string`
611611
from line 626
626626
627627 The caller-assigned identifier for this download, stable across the state changes reporting it.
628628
629 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
629 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
630630
631631 - `url: string`
632632
from line 638
638638
639639 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
640640
641 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
641 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
642642
643643 - `size_bytes: optional number or null`
644644
from line 656
656656
657657 The caller-assigned identifier for this download, stable across the state changes reporting it.
658658
659 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
659 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
660660
661661 - `url: string`
662662
from line 668
668668
669669 The failure or cancellation detail, when known.
670670
671 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
671 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
672672
673673 - `is_error: optional boolean`
674674
from line 676
676676
677677 For a toolset member tool_result, the toolset family of the paired tool_use.
678678
679 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
679 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
680680
681681 - `ServerToolUseBlockParam object`
682682
from line 1054
10541054
10551055 - `tool_name: string`
10561056
1057 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
1057 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
10581058
10591059 - `cache_control: optional CacheControlEphemeral or null`
10601060
from line 1095
10951095
10961096 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10971097
1098 - `string`
1099
10981100 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10991101
11001102 The model that will complete your prompt.
from line 1139
11371139
11381140 Powerful intelligence for long-running agents and coding
11391141
1140 - `"claude-mythos-preview"`
1141
1142 New class of intelligence, strongest in coding and cybersecurity
1143
11441142 - `"claude-opus-4-6"`
11451143
11461144 Powerful intelligence for long-running agents and coding
from line 1171
11731171
11741172 High-performance model for agents and coding
11751173
1176 - `string`
1174 - `"claude-mythos-preview"`
11771175
1176 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
1177
1178 New class of intelligence, strongest in coding and cybersecurity
1179
11781180 - `cache_control: optional CacheControlEphemeral or null`
11791181
11801182 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 1211
12091211
12101212 Skill ID
12111213
1212 maxLength: 64, minLength: 1
1214 minLength: 1, maxLength: 64
12131215
12141216 - `version: optional string`
12151217
12161218 Skill version or 'latest' for most recent version
12171219
1218 maxLength: 64, minLength: 1
1220 minLength: 1, maxLength: 64
12191221
12201222 - `string`
12211223
12221224 - `diagnostics: optional DiagnosticsParam or null`
12231225
1224 Request-level diagnostics. Currently carries the previous response
1225 id for prompt-cache divergence reporting.
1226 Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request.
12261227
12271228 - `previous_message_id: optional string or null`
12281229
from line 1253
12521253
12531254 - `effort: optional "low" or "medium" or "high" or 2 more or null`
12541255
1255 All possible effort levels.
1256 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
12561257
1258 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
1259
12571260 - `"low"`
12581261
12591262 - `"medium"`
from line 1505
15021505
15031506 This is how the tool will be called by the model and in `tool_use` blocks.
15041507
1505 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
1508 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
15061509
15071510 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
15081511
from line 1722
17191722
17201723 - `configs: optional BrowserToolsetConfigs or null`
17211724
1722 Per-member configuration for `browser_toolset_20260801`: one
1723 optional field per member tool, keyed by the member name — the same
1724 name the member's `tool_use` blocks carry. Every member is an
1725 accepted key, and a member's defaults apply wherever its key is
1726 absent. Unknown keys are rejected: the field set is this toolset
1727 version's complete member set.
1725 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
17281726
17291727 - `type: optional BrowserTypeConfig or null`
17301728
from line 2149
21512149
21522150 - `configs: optional ComputerToolsetConfigs or null`
21532151
2154 Per-member configuration for `computer_toolset_20260801`: one
2155 optional field per member tool, keyed by the member name — the same
2156 name the member's `tool_use` blocks carry. Every member is an
2157 accepted key, and a member's defaults apply wherever its key is
2158 absent. Unknown keys are rejected: the field set is this toolset
2159 version's complete member set.
2152 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
21602153
21612154 - `type: optional ComputerTypeConfig or null`
21622155
from line 2503
25102503
25112504 Maximum number of times the tool can be used in the API request.
25122505
2513 exclusiveMinimum: 0
2506 minimum: 1
25142507
25152508 - `strict: optional boolean`
25162509
from line 2519
25262519
25272520 The city of the user.
25282521
2529 maxLength: 255, minLength: 1
2522 minLength: 1, maxLength: 255
25302523
25312524 - `country: optional string or null`
25322525
25332526 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
25342527
2535 maxLength: 2, minLength: 2
2528 minLength: 2, maxLength: 2
25362529
25372530 - `region: optional string or null`
25382531
25392532 The region of the user.
25402533
2541 maxLength: 255, minLength: 1
2534 minLength: 1, maxLength: 255
25422535
25432536 - `timezone: optional string or null`
25442537
25452538 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
25462539
2547 maxLength: 255, minLength: 1
2540 minLength: 1, maxLength: 255
25482541
25492542 - `WebFetchTool20250910 object`
25502543
from line 2583
25902583
25912584 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
25922585
2593 exclusiveMinimum: 0
2586 minimum: 1
25942587
25952588 - `max_uses: optional number or null`
25962589
25972590 Maximum number of times the tool can be used in the API request.
25982591
2599 exclusiveMinimum: 0
2592 minimum: 1
26002593
26012594 - `strict: optional boolean`
26022595
from line 2597
26042597
26052598 - `url_sources: optional WebFetchURLSources or null`
26062599
2607 Which sources contribute to the set of URLs web fetch may fetch.
2600 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
26082601
2609 Each key is a tagged variant: `user_input` is `all` or `none`; the
2610 two tool filters are `all`, `none`, `only` (only the named tools'
2611 results) or `except` (every result but the named tools'). A named tool
2612 must be declared in this request's `tools[]`.
2613
26142602 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
26152603
26162604 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 2721
27332721
27342722 Maximum number of times the tool can be used in the API request.
27352723
2736 exclusiveMinimum: 0
2724 minimum: 1
27372725
27382726 - `strict: optional boolean`
27392727
from line 2775
27872775
27882776 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
27892777
2790 exclusiveMinimum: 0
2778 minimum: 1
27912779
27922780 - `max_uses: optional number or null`
27932781
27942782 Maximum number of times the tool can be used in the API request.
27952783
2796 exclusiveMinimum: 0
2784 minimum: 1
27972785
27982786 - `strict: optional boolean`
27992787
from line 2789
28012789
28022790 - `url_sources: optional WebFetchURLSources or null`
28032791
2804 Which sources contribute to the set of URLs web fetch may fetch.
2792 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28052793
2806 Each key is a tagged variant: `user_input` is `all` or `none`; the
2807 two tool filters are `all`, `none`, `only` (only the named tools'
2808 results) or `except` (every result but the named tools'). A named tool
2809 must be declared in this request's `tools[]`.
2810
28112794 - `WebFetchTool20260309 object`
28122795
28132796 Web fetch tool with use_cache parameter for bypassing cached content.
from line 2837
28542837
28552838 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
28562839
2857 exclusiveMinimum: 0
2840 minimum: 1
28582841
28592842 - `max_uses: optional number or null`
28602843
28612844 Maximum number of times the tool can be used in the API request.
28622845
2863 exclusiveMinimum: 0
2846 minimum: 1
28642847
28652848 - `strict: optional boolean`
28662849
from line 2851
28682851
28692852 - `url_sources: optional WebFetchURLSources or null`
28702853
2871 Which sources contribute to the set of URLs web fetch may fetch.
2854 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28722855
2873 Each key is a tagged variant: `user_input` is `all` or `none`; the
2874 two tool filters are `all`, `none`, `only` (only the named tools'
2875 results) or `except` (every result but the named tools'). A named tool
2876 must be declared in this request's `tools[]`.
2877
28782856 - `use_cache: optional boolean`
28792857
28802858 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 2897
29192897
29202898 Maximum number of times the tool can be used in the API request.
29212899
2922 exclusiveMinimum: 0
2900 minimum: 1
29232901
29242902 - `response_inclusion: optional "full" or "excluded"`
29252903
from line 2959
29812959
29822960 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
29832961
2984 exclusiveMinimum: 0
2962 minimum: 1
29852963
29862964 - `max_uses: optional number or null`
29872965
29882966 Maximum number of times the tool can be used in the API request.
29892967
2990 exclusiveMinimum: 0
2968 minimum: 1
29912969
29922970 - `response_inclusion: optional "full" or "excluded"`
29932971
from line 2981
30032981
30042982 - `url_sources: optional WebFetchURLSources or null`
30052983
3006 Which sources contribute to the set of URLs web fetch may fetch.
2984 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
30072985
3008 Each key is a tagged variant: `user_input` is `all` or `none`; the
3009 two tool filters are `all`, `none`, `only` (only the named tools'
3010 results) or `except` (every result but the named tools'). A named tool
3011 must be declared in this request's `tools[]`.
3012
30132986 - `use_cache: optional boolean`
30142987
30152988 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 3069
30963069
30973070 Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
30983071
3099 maximum: 1, minimum: 0
3072 minimum: 0, maximum: 1
31003073
31013074 - `top_k: optional number`
31023075
from line 3093
31203093
31213094 Recommended for advanced use cases only.
31223095
3123 maximum: 1, minimum: 0
3096 minimum: 0, maximum: 1
31243097
31253098### Returns
31263099
from line 3441
34683441
34693442 Defaults to `20`. Ranges from `1` to `1000`.
34703443
3471 default: 20, maximum: 1000, minimum: 1
3444 default: 20, minimum: 1, maximum: 1000
34723445
34733446### Headers
34743447
from line 3901
39283901
39293902 - `container: Container or null`
39303903
3931 Information about the container used in the request (for the code execution tool)
3904 Information about the container used in this request.
39323905
3906 This will be non-null if a container tool (e.g. code execution) was used.
3907
39333908 - `id: string`
39343909
39353910 Identifier for the container used in this request
from line 3931
39563931
39573932 Skill ID
39583933
3959 maxLength: 64, minLength: 1
3934 minLength: 1, maxLength: 64
39603935
39613936 - `version: string`
39623937
39633938 The resolved version: a skill version ID for custom skills.
39643939
3965 maxLength: 64, minLength: 1
3940 minLength: 1, maxLength: 64
39663941
39673942 - `content: array of ContentBlock`
39683943
from line 4110
41354110
41364111 - `text: string`
41374112
4138 minLength: 0
4139
41404113 - `ThinkingBlock object`
41414114
41424115 - `type: "thinking"`
from line 4190
42174190
42184191 For a toolset member tool_use, the toolset family.
42194192
4220 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
4193 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
42214194
42224195 - `ServerToolUseBlock object`
42234196
from line 4638
46654638
46664639 - `tool_name: string`
46674640
4668 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
4641 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
46694642
46704643 - `tool_use_id: string`
46714644
from line 4656
46834656
46844657 - `diagnostics: Diagnostics or null`
46854658
4686 Request-level diagnostics: why the prompt cache could not fully reuse
4687 the prefix of the request named by `diagnostics.previous_message_id`.
4659 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
46884660
46894661 - `cache_miss_reason: CacheMissReason or null`
46904662
from line 4720
47484720
47494721 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
47504722
4723 - `string`
4724
47514725 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
47524726
47534727 The model that will complete your prompt.
from line 4764
47904764
47914765 Powerful intelligence for long-running agents and coding
47924766
4793 - `"claude-mythos-preview"`
4794
4795 New class of intelligence, strongest in coding and cybersecurity
4796
47974767 - `"claude-opus-4-6"`
47984768
47994769 Powerful intelligence for long-running agents and coding
from line 4796
48264796
48274797 High-performance model for agents and coding
48284798
4829 - `string`
4799 - `"claude-mythos-preview"`
48304800
4801 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
4802
4803 New class of intelligence, strongest in coding and cybersecurity
4804
48314805 - `role: "assistant"`
48324806
48334807 Conversational role of the generated message.
from line 4812
48384812
48394813 - `stop_details: RefusalStopDetails or null`
48404814
4841 Structured information about a refusal.
4815 Structured information about why model output stopped.
48424816
4817 This is `null` when the `stop_reason` has no additional detail to report.
4818
48434819 - `type: "refusal"`
48444820
48454821 default: refusal
from line 4822
48464822
48474823 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
48484824
4849 The policy category that triggered a refusal.
4825 The policy category that triggered the refusal.
48504826
4827 `null` when the refusal doesn't map to a named category.
4828
48514829 - `"cyber"`
48524830
48534831 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
from line 5412
54345412
54355413 - `container: Container or null`
54365414
5437 Information about the container used in the request (for the code execution tool)
5415 Information about the container used in this request.
54385416
5417 This will be non-null if a container tool (e.g. code execution) was used.
5418
54395419 - `id: string`
54405420
54415421 Identifier for the container used in this request
from line 5442
54625442
54635443 Skill ID
54645444
5465 maxLength: 64, minLength: 1
5445 minLength: 1, maxLength: 64
54665446
54675447 - `version: string`
54685448
54695449 The resolved version: a skill version ID for custom skills.
54705450
5471 maxLength: 64, minLength: 1
5451 minLength: 1, maxLength: 64
54725452
54735453 - `content: array of ContentBlock`
54745454
from line 5621
56415621
56425622 - `text: string`
56435623
5644 minLength: 0
5645
56465624 - `ThinkingBlock object`
56475625
56485626 - `type: "thinking"`
from line 5701
57235701
57245702 For a toolset member tool_use, the toolset family.
57255703
5726 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
5704 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
57275705
57285706 - `ServerToolUseBlock object`
57295707
from line 6149
61716149
61726150 - `tool_name: string`
61736151
6174 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
6152 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
61756153
61766154 - `tool_use_id: string`
61776155
from line 6167
61896167
61906168 - `diagnostics: Diagnostics or null`
61916169
6192 Request-level diagnostics: why the prompt cache could not fully reuse
6193 the prefix of the request named by `diagnostics.previous_message_id`.
6170 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
61946171
61956172 - `cache_miss_reason: CacheMissReason or null`
61966173
from line 6231
62546231
62556232 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
62566233
6234 - `string`
6235
62576236 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
62586237
62596238 The model that will complete your prompt.
from line 6275
62966275
62976276 Powerful intelligence for long-running agents and coding
62986277
6299 - `"claude-mythos-preview"`
6300
6301 New class of intelligence, strongest in coding and cybersecurity
6302
63036278 - `"claude-opus-4-6"`
63046279
63056280 Powerful intelligence for long-running agents and coding
from line 6307
63326307
63336308 High-performance model for agents and coding
63346309
6335 - `string`
6310 - `"claude-mythos-preview"`
63366311
6312 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
6313
6314 New class of intelligence, strongest in coding and cybersecurity
6315
63376316 - `role: "assistant"`
63386317
63396318 Conversational role of the generated message.
from line 6323
63446323
63456324 - `stop_details: RefusalStopDetails or null`
63466325
6347 Structured information about a refusal.
6326 Structured information about why model output stopped.
63486327
6328 This is `null` when the `stop_reason` has no additional detail to report.
6329
63496330 - `type: "refusal"`
63506331
63516332 default: refusal
from line 6333
63526333
63536334 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
63546335
6355 The policy category that triggered a refusal.
6336 The policy category that triggered the refusal.
63566337
6338 `null` when the refusal doesn't map to a named category.
6339
63576340 - `"cyber"`
63586341
63596342 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
from line 6695
67126695
67136696 - `container: Container or null`
67146697
6715 Information about the container used in the request (for the code execution tool)
6698 Information about the container used in this request.
67166699
6700 This will be non-null if a container tool (e.g. code execution) was used.
6701
67176702 - `id: string`
67186703
67196704 Identifier for the container used in this request
from line 6725
67406725
67416726 Skill ID
67426727
6743 maxLength: 64, minLength: 1
6728 minLength: 1, maxLength: 64
67446729
67456730 - `version: string`
67466731
67476732 The resolved version: a skill version ID for custom skills.
67486733
6749 maxLength: 64, minLength: 1
6734 minLength: 1, maxLength: 64
67506735
67516736 - `content: array of ContentBlock`
67526737
from line 6904
69196904
69206905 - `text: string`
69216906
6922 minLength: 0
6923
69246907 - `ThinkingBlock object`
69256908
69266909 - `type: "thinking"`
from line 6984
70016984
70026985 For a toolset member tool_use, the toolset family.
70036986
7004 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
6987 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
70056988
70066989 - `ServerToolUseBlock object`
70076990
from line 7432
74497432
74507433 - `tool_name: string`
74517434
7452 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
7435 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
74537436
74547437 - `tool_use_id: string`
74557438
from line 7450
74677450
74687451 - `diagnostics: Diagnostics or null`
74697452
7470 Request-level diagnostics: why the prompt cache could not fully reuse
7471 the prefix of the request named by `diagnostics.previous_message_id`.
7453 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
74727454
74737455 - `cache_miss_reason: CacheMissReason or null`
74747456
from line 7514
75327514
75337515 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
75347516
7517 - `string`
7518
75357519 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
75367520
75377521 The model that will complete your prompt.
from line 7558
75747558
75757559 Powerful intelligence for long-running agents and coding
75767560
7577 - `"claude-mythos-preview"`
7578
7579 New class of intelligence, strongest in coding and cybersecurity
7580
75817561 - `"claude-opus-4-6"`
75827562
75837563 Powerful intelligence for long-running agents and coding
from line 7590
76107590
76117591 High-performance model for agents and coding
76127592
7613 - `string`
7593 - `"claude-mythos-preview"`
76147594
7595 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
7596
7597 New class of intelligence, strongest in coding and cybersecurity
7598
76157599 - `role: "assistant"`
76167600
76177601 Conversational role of the generated message.
from line 7606
76227606
76237607 - `stop_details: RefusalStopDetails or null`
76247608
7625 Structured information about a refusal.
7609 Structured information about why model output stopped.
76267610
7611 This is `null` when the `stop_reason` has no additional detail to report.
7612
76277613 - `type: "refusal"`
76287614
76297615 default: refusal
from line 7616
76307616
76317617 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
76327618
7633 The policy category that triggered a refusal.
7619 The policy category that triggered the refusal.
76347620
7621 `null` when the refusal doesn't map to a named category.
7622
76357623 - `"cyber"`
76367624
76377625 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
from line 7930
79427930
79437931 - `container: Container or null`
79447932
7945 Information about the container used in the request (for the code execution tool)
7933 Information about the container used in this request.
79467934
7935 This will be non-null if a container tool (e.g. code execution) was used.
7936
79477937 - `id: string`
79487938
79497939 Identifier for the container used in this request
from line 7960
79707960
79717961 Skill ID
79727962
7973 maxLength: 64, minLength: 1
7963 minLength: 1, maxLength: 64
79747964
79757965 - `version: string`
79767966
79777967 The resolved version: a skill version ID for custom skills.
79787968
7979 maxLength: 64, minLength: 1
7969 minLength: 1, maxLength: 64
79807970
79817971 - `content: array of ContentBlock`
79827972
from line 8139
81498139
81508140 - `text: string`
81518141
8152 minLength: 0
8153
81548142 - `ThinkingBlock object`
81558143
81568144 - `type: "thinking"`
from line 8219
82318219
82328220 For a toolset member tool_use, the toolset family.
82338221
8234 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
8222 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
82358223
82368224 - `ServerToolUseBlock object`
82378225
from line 8667
86798667
86808668 - `tool_name: string`
86818669
8682 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
8670 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
86838671
86848672 - `tool_use_id: string`
86858673
from line 8685
86978685
86988686 - `diagnostics: Diagnostics or null`
86998687
8700 Request-level diagnostics: why the prompt cache could not fully reuse
8701 the prefix of the request named by `diagnostics.previous_message_id`.
8688 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
87028689
87038690 - `cache_miss_reason: CacheMissReason or null`
87048691
from line 8721
87348721
87358722 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
87368723
8737 - `
8724 - `CacheMissMessagesChanged object`
8725
8726 - `type
api/messages/batches/create Changed · +125 / -152 lines
from line 31
3131
3232 List of requests for prompt completion. Each is an individual request to create a Message.
3333
34 maxItems: 100000, minItems: 1
34 minItems: 1, maxItems: 100000
3535
3636 - `custom_id: string`
3737
from line 39
3939
4040 Must be unique for each request within the Message Batch.
4141
42 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,64}$
42 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]{1,64}$
4343
4444 - `params: object`
4545
from line 159
159159
160160 - `document_title: string or null`
161161
162 maxLength: 500, minLength: 1
162 minLength: 1, maxLength: 500
163163
164164 - `end_char_index: number`
165165
from line 179
179179
180180 - `document_title: string or null`
181181
182 maxLength: 500, minLength: 1
182 minLength: 1, maxLength: 500
183183
184184 - `end_page_number: number`
185185
from line 203
203203
204204 - `document_title: string or null`
205205
206 maxLength: 500, minLength: 1
206 minLength: 1, maxLength: 500
207207
208208 - `end_block_index: number`
209209
from line 227
227227
228228 - `title: string or null`
229229
230 maxLength: 512, minLength: 1
230 minLength: 1, maxLength: 512
231231
232232 - `url: string`
233233
from line 383
383383
384384 - `title: optional string or null`
385385
386 maxLength: 500, minLength: 1
386 minLength: 1, maxLength: 500
387387
388388 - `SearchResultBlockParam object`
389389
from line 447
447447
448448 - `name: string`
449449
450 maxLength: 200, minLength: 1
450 minLength: 1, maxLength: 200
451451
452452 - `cache_control: optional CacheControlEphemeral or null`
453453
from line 483
483483
484484 For a toolset member tool_use, the toolset family this member belongs to.
485485
486 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
486 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
487487
488488 - `ToolResultBlockParam object`
489489
from line 519
519519
520520 - `tool_name: string`
521521
522 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
522 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
523523
524524 - `cache_control: optional CacheControlEphemeral or null`
525525
from line 547
547547
548548 The caller-assigned identifier for this tab, unique within the inventory.
549549
550 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
550 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
551551
552552 - `title: string`
553553
from line 573
573573
574574 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
575575
576 maxItems: 200, minItems: 1
576 minItems: 1, maxItems: 200
577577
578578 - `BrowserStateChangeTabOpened object`
579579
from line 591
591591
592592 The `tab_id` of the opened tab, present in `tabs`.
593593
594 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
594 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
595595
596596 - `BrowserStateChangeDownloadStarted object`
597597
from line 603
603603
604604 The caller-assigned identifier for this download, stable across the state changes reporting it.
605605
606 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
606 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
607607
608608 - `url: string`
609609
from line 624
624624
625625 The caller-assigned identifier for this download, stable across the state changes reporting it.
626626
627 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
627 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
628628
629629 - `url: string`
630630
from line 636
636636
637637 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
638638
639 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
639 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
640640
641641 - `size_bytes: optional number or null`
642642
from line 654
654654
655655 The caller-assigned identifier for this download, stable across the state changes reporting it.
656656
657 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
657 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
658658
659659 - `url: string`
660660
from line 666
666666
667667 The failure or cancellation detail, when known.
668668
669 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
669 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
670670
671671 - `is_error: optional boolean`
672672
from line 674
674674
675675 For a toolset member tool_result, the toolset family of the paired tool_use.
676676
677 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
677 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
678678
679679 - `ServerToolUseBlockParam object`
680680
from line 1052
10521052
10531053 - `tool_name: string`
10541054
1055 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
1055 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
10561056
10571057 - `cache_control: optional CacheControlEphemeral or null`
10581058
from line 1093
10931093
10941094 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10951095
1096 - `string`
1097
10961098 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10971099
10981100 The model that will complete your prompt.
from line 1137
11351137
11361138 Powerful intelligence for long-running agents and coding
11371139
1138 - `"claude-mythos-preview"`
1139
1140 New class of intelligence, strongest in coding and cybersecurity
1141
11421140 - `"claude-opus-4-6"`
11431141
11441142 Powerful intelligence for long-running agents and coding
from line 1169
11711169
11721170 High-performance model for agents and coding
11731171
1174 - `string`
1172 - `"claude-mythos-preview"`
11751173
1174 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
1175
1176 New class of intelligence, strongest in coding and cybersecurity
1177
11761178 - `cache_control: optional CacheControlEphemeral or null`
11771179
11781180 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 1209
12071209
12081210 Skill ID
12091211
1210 maxLength: 64, minLength: 1
1212 minLength: 1, maxLength: 64
12111213
12121214 - `version: optional string`
12131215
12141216 Skill version or 'latest' for most recent version
12151217
1216 maxLength: 64, minLength: 1
1218 minLength: 1, maxLength: 64
12171219
12181220 - `string`
12191221
12201222 - `diagnostics: optional DiagnosticsParam or null`
12211223
1222 Request-level diagnostics. Currently carries the previous response
1223 id for prompt-cache divergence reporting.
1224 Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request.
12241225
12251226 - `previous_message_id: optional string or null`
12261227
from line 1251
12501251
12511252 - `effort: optional "low" or "medium" or "high" or 2 more or null`
12521253
1253 All possible effort levels.
1254 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
12541255
1256 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
1257
12551258 - `"low"`
12561259
12571260 - `"medium"`
from line 1503
15001503
15011504 This is how the tool will be called by the model and in `tool_use` blocks.
15021505
1503 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
1506 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
15041507
15051508 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
15061509
from line 1720
17171720
17181721 - `configs: optional BrowserToolsetConfigs or null`
17191722
1720 Per-member configuration for `browser_toolset_20260801`: one
1721 optional field per member tool, keyed by the member name — the same
1722 name the member's `tool_use` blocks carry. Every member is an
1723 accepted key, and a member's defaults apply wherever its key is
1724 absent. Unknown keys are rejected: the field set is this toolset
1725 version's complete member set.
1723 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
17261724
17271725 - `type: optional BrowserTypeConfig or null`
17281726
from line 2147
21492147
21502148 - `configs: optional ComputerToolsetConfigs or null`
21512149
2152 Per-member configuration for `computer_toolset_20260801`: one
2153 optional field per member tool, keyed by the member name — the same
2154 name the member's `tool_use` blocks carry. Every member is an
2155 accepted key, and a member's defaults apply wherever its key is
2156 absent. Unknown keys are rejected: the field set is this toolset
2157 version's complete member set.
2150 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
21582151
21592152 - `type: optional ComputerTypeConfig or null`
21602153
from line 2501
25082501
25092502 Maximum number of times the tool can be used in the API request.
25102503
2511 exclusiveMinimum: 0
2504 minimum: 1
25122505
25132506 - `strict: optional boolean`
25142507
from line 2517
25242517
25252518 The city of the user.
25262519
2527 maxLength: 255, minLength: 1
2520 minLength: 1, maxLength: 255
25282521
25292522 - `country: optional string or null`
25302523
25312524 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
25322525
2533 maxLength: 2, minLength: 2
2526 minLength: 2, maxLength: 2
25342527
25352528 - `region: optional string or null`
25362529
25372530 The region of the user.
25382531
2539 maxLength: 255, minLength: 1
2532 minLength: 1, maxLength: 255
25402533
25412534 - `timezone: optional string or null`
25422535
25432536 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
25442537
2545 maxLength: 255, minLength: 1
2538 minLength: 1, maxLength: 255
25462539
25472540 - `WebFetchTool20250910 object`
25482541
from line 2581
25882581
25892582 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
25902583
2591 exclusiveMinimum: 0
2584 minimum: 1
25922585
25932586 - `max_uses: optional number or null`
25942587
25952588 Maximum number of times the tool can be used in the API request.
25962589
2597 exclusiveMinimum: 0
2590 minimum: 1
25982591
25992592 - `strict: optional boolean`
26002593
from line 2595
26022595
26032596 - `url_sources: optional WebFetchURLSources or null`
26042597
2605 Which sources contribute to the set of URLs web fetch may fetch.
2598 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
26062599
2607 Each key is a tagged variant: `user_input` is `all` or `none`; the
2608 two tool filters are `all`, `none`, `only` (only the named tools'
2609 results) or `except` (every result but the named tools'). A named tool
2610 must be declared in this request's `tools[]`.
2611
26122600 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
26132601
26142602 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 2719
27312719
27322720 Maximum number of times the tool can be used in the API request.
27332721
2734 exclusiveMinimum: 0
2722 minimum: 1
27352723
27362724 - `strict: optional boolean`
27372725
from line 2773
27852773
27862774 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
27872775
2788 exclusiveMinimum: 0
2776 minimum: 1
27892777
27902778 - `max_uses: optional number or null`
27912779
27922780 Maximum number of times the tool can be used in the API request.
27932781
2794 exclusiveMinimum: 0
2782 minimum: 1
27952783
27962784 - `strict: optional boolean`
27972785
from line 2787
27992787
28002788 - `url_sources: optional WebFetchURLSources or null`
28012789
2802 Which sources contribute to the set of URLs web fetch may fetch.
2790 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28032791
2804 Each key is a tagged variant: `user_input` is `all` or `none`; the
2805 two tool filters are `all`, `none`, `only` (only the named tools'
2806 results) or `except` (every result but the named tools'). A named tool
2807 must be declared in this request's `tools[]`.
2808
28092792 - `WebFetchTool20260309 object`
28102793
28112794 Web fetch tool with use_cache parameter for bypassing cached content.
from line 2835
28522835
28532836 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
28542837
2855 exclusiveMinimum: 0
2838 minimum: 1
28562839
28572840 - `max_uses: optional number or null`
28582841
28592842 Maximum number of times the tool can be used in the API request.
28602843
2861 exclusiveMinimum: 0
2844 minimum: 1
28622845
28632846 - `strict: optional boolean`
28642847
from line 2849
28662849
28672850 - `url_sources: optional WebFetchURLSources or null`
28682851
2869 Which sources contribute to the set of URLs web fetch may fetch.
2852 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28702853
2871 Each key is a tagged variant: `user_input` is `all` or `none`; the
2872 two tool filters are `all`, `none`, `only` (only the named tools'
2873 results) or `except` (every result but the named tools'). A named tool
2874 must be declared in this request's `tools[]`.
2875
28762854 - `use_cache: optional boolean`
28772855
28782856 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 2895
29172895
29182896 Maximum number of times the tool can be used in the API request.
29192897
2920 exclusiveMinimum: 0
2898 minimum: 1
29212899
29222900 - `response_inclusion: optional "full" or "excluded"`
29232901
from line 2957
29792957
29802958 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
29812959
2982 exclusiveMinimum: 0
2960 minimum: 1
29832961
29842962 - `max_uses: optional number or null`
29852963
29862964 Maximum number of times the tool can be used in the API request.
29872965
2988 exclusiveMinimum: 0
2966 minimum: 1
29892967
29902968 - `response_inclusion: optional "full" or "excluded"`
29912969
from line 2979
30012979
30022980 - `url_sources: optional WebFetchURLSources or null`
30032981
3004 Which sources contribute to the set of URLs web fetch may fetch.
2982 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
30052983
3006 Each key is a tagged variant: `user_input` is `all` or `none`; the
3007 two tool filters are `all`, `none`, `only` (only the named tools'
3008 results) or `except` (every result but the named tools'). A named tool
3009 must be declared in this request's `tools[]`.
3010
30112984 - `use_cache: optional boolean`
30122985
30132986 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 3067
30943067
30953068 Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
30963069
3097 maximum: 1, minimum: 0
3070 minimum: 0, maximum: 1
30983071
30993072 - `top_k: optional number`
31003073
from line 3091
31183091
31193092 Recommended for advanced use cases only.
31203093
3121 maximum: 1, minimum: 0
3094 minimum: 0, maximum: 1
31223095
31233096## Returns
31243097
api/messages/batches/results Changed · +50 / -45 lines
from line 69
6969
7070 - `container: Container or null`
7171
72 Information about the container used in the request (for the code execution tool)
72 Information about the container used in this request.
7373
74 This will be non-null if a container tool (e.g. code execution) was used.
75
7476 - `id: string`
7577
7678 Identifier for the container used in this request
from line 99
9799
98100 Skill ID
99101
100 maxLength: 64, minLength: 1
102 minLength: 1, maxLength: 64
101103
102104 - `version: string`
103105
104106 The resolved version: a skill version ID for custom skills.
105107
106 maxLength: 64, minLength: 1
108 minLength: 1, maxLength: 64
107109
108110 - `content: array of ContentBlock`
109111
from line 278
276278
277279 - `text: string`
278280
279 minLength: 0
280
281281 - `ThinkingBlock object`
282282
283283 - `type: "thinking"`
from line 358
358358
359359 For a toolset member tool_use, the toolset family.
360360
361 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
361 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
362362
363363 - `ServerToolUseBlock object`
364364
from line 806
806806
807807 - `tool_name: string`
808808
809 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
809 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
810810
811811 - `tool_use_id: string`
812812
from line 824
824824
825825 - `diagnostics: Diagnostics or null`
826826
827 Request-level diagnostics: why the prompt cache could not fully reuse
828 the prefix of the request named by `diagnostics.previous_message_id`.
827 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
829828
830829 - `cache_miss_reason: CacheMissReason or null`
831830
from line 888
889888
890889 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
891890
891 - `string`
892
892893 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
893894
894895 The model that will complete your prompt.
from line 932
931932
932933 Powerful intelligence for long-running agents and coding
933934
934 - `"claude-mythos-preview"`
935
936 New class of intelligence, strongest in coding and cybersecurity
937
938935 - `"claude-opus-4-6"`
939936
940937 Powerful intelligence for long-running agents and coding
from line 964
967964
968965 High-performance model for agents and coding
969966
970 - `string`
967 - `"claude-mythos-preview"`
971968
969 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
970
971 New class of intelligence, strongest in coding and cybersecurity
972
972973 - `role: "assistant"`
973974
974975 Conversational role of the generated message.
from line 980
979980
980981 - `stop_details: RefusalStopDetails or null`
981982
982 Structured information about a refusal.
983 Structured information about why model output stopped.
983984
985 This is `null` when the `stop_reason` has no additional detail to report.
986
984987 - `type: "refusal"`
985988
986989 default: refusal
from line 990
987990
988991 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
989992
990 The policy category that triggered a refusal.
993 The policy category that triggered the refusal.
994
995 `null` when the refusal doesn't map to a named category.
991996
992997 - `"cyber"`
993998
api/messages/count_tokens Changed · +79 / -105 lines
from line 127
127127
128128 - `document_title: string or null`
129129
130 maxLength: 500, minLength: 1
130 minLength: 1, maxLength: 500
131131
132132 - `end_char_index: number`
133133
from line 147
147147
148148 - `document_title: string or null`
149149
150 maxLength: 500, minLength: 1
150 minLength: 1, maxLength: 500
151151
152152 - `end_page_number: number`
153153
from line 171
171171
172172 - `document_title: string or null`
173173
174 maxLength: 500, minLength: 1
174 minLength: 1, maxLength: 500
175175
176176 - `end_block_index: number`
177177
from line 195
195195
196196 - `title: string or null`
197197
198 maxLength: 512, minLength: 1
198 minLength: 1, maxLength: 512
199199
200200 - `url: string`
201201
from line 351
351351
352352 - `title: optional string or null`
353353
354 maxLength: 500, minLength: 1
354 minLength: 1, maxLength: 500
355355
356356 - `SearchResultBlockParam object`
357357
from line 415
415415
416416 - `name: string`
417417
418 maxLength: 200, minLength: 1
418 minLength: 1, maxLength: 200
419419
420420 - `cache_control: optional CacheControlEphemeral or null`
421421
from line 451
451451
452452 For a toolset member tool_use, the toolset family this member belongs to.
453453
454 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
454 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
455455
456456 - `ToolResultBlockParam object`
457457
from line 487
487487
488488 - `tool_name: string`
489489
490 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
490 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
491491
492492 - `cache_control: optional CacheControlEphemeral or null`
493493
from line 515
515515
516516 The caller-assigned identifier for this tab, unique within the inventory.
517517
518 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
518 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
519519
520520 - `title: string`
521521
from line 541
541541
542542 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
543543
544 maxItems: 200, minItems: 1
544 minItems: 1, maxItems: 200
545545
546546 - `BrowserStateChangeTabOpened object`
547547
from line 559
559559
560560 The `tab_id` of the opened tab, present in `tabs`.
561561
562 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
562 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
563563
564564 - `BrowserStateChangeDownloadStarted object`
565565
from line 571
571571
572572 The caller-assigned identifier for this download, stable across the state changes reporting it.
573573
574 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
574 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
575575
576576 - `url: string`
577577
from line 592
592592
593593 The caller-assigned identifier for this download, stable across the state changes reporting it.
594594
595 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
595 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
596596
597597 - `url: string`
598598
from line 604
604604
605605 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
606606
607 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
607 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
608608
609609 - `size_bytes: optional number or null`
610610
from line 622
622622
623623 The caller-assigned identifier for this download, stable across the state changes reporting it.
624624
625 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
625 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
626626
627627 - `url: string`
628628
from line 634
634634
635635 The failure or cancellation detail, when known.
636636
637 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
637 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
638638
639639 - `is_error: optional boolean`
640640
from line 642
642642
643643 For a toolset member tool_result, the toolset family of the paired tool_use.
644644
645 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
645 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
646646
647647 - `ServerToolUseBlockParam object`
648648
from line 1020
10201020
10211021 - `tool_name: string`
10221022
1023 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
1023 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
10241024
10251025 - `cache_control: optional CacheControlEphemeral or null`
10261026
from line 1061
10611061
10621062 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10631063
1064 - `string`
1065
10641066 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10651067
10661068 The model that will complete your prompt.
from line 1105
11031105
11041106 Powerful intelligence for long-running agents and coding
11051107
1106 - `"claude-mythos-preview"`
1107
1108 New class of intelligence, strongest in coding and cybersecurity
1109
11101108 - `"claude-opus-4-6"`
11111109
11121110 Powerful intelligence for long-running agents and coding
from line 1137
11391137
11401138 High-performance model for agents and coding
11411139
1142 - `string`
1140 - `"claude-mythos-preview"`
11431141
1142 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
1143
1144 New class of intelligence, strongest in coding and cybersecurity
1145
11441146- `cache_control: optional CacheControlEphemeral or null`
11451147
11461148 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 1153
11511153
11521154 - `effort: optional "low" or "medium" or "high" or 2 more or null`
11531155
1154 All possible effort levels.
1156 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
11551157
1158 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
1159
11561160 - `"low"`
11571161
11581162 - `"medium"`
from line 1381
13771381
13781382 This is how the tool will be called by the model and in `tool_use` blocks.
13791383
1380 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
1384 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
13811385
13821386 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
13831387
from line 1598
15941598
15951599 - `configs: optional BrowserToolsetConfigs or null`
15961600
1597 Per-member configuration for `browser_toolset_20260801`: one
1598 optional field per member tool, keyed by the member name — the same
1599 name the member's `tool_use` blocks carry. Every member is an
1600 accepted key, and a member's defaults apply wherever its key is
1601 absent. Unknown keys are rejected: the field set is this toolset
1602 version's complete member set.
1601 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
16031602
16041603 - `type: optional BrowserTypeConfig or null`
16051604
from line 2025
20262025
20272026 - `configs: optional ComputerToolsetConfigs or null`
20282027
2029 Per-member configuration for `computer_toolset_20260801`: one
2030 optional field per member tool, keyed by the member name — the same
2031 name the member's `tool_use` blocks carry. Every member is an
2032 accepted key, and a member's defaults apply wherever its key is
2033 absent. Unknown keys are rejected: the field set is this toolset
2034 version's complete member set.
2028 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
20352029
20362030 - `type: optional ComputerTypeConfig or null`
20372031
from line 2379
23852379
23862380 Maximum number of times the tool can be used in the API request.
23872381
2388 exclusiveMinimum: 0
2382 minimum: 1
23892383
23902384 - `strict: optional boolean`
23912385
from line 2395
24012395
24022396 The city of the user.
24032397
2404 maxLength: 255, minLength: 1
2398 minLength: 1, maxLength: 255
24052399
24062400 - `country: optional string or null`
24072401
24082402 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
24092403
2410 maxLength: 2, minLength: 2
2404 minLength: 2, maxLength: 2
24112405
24122406 - `region: optional string or null`
24132407
24142408 The region of the user.
24152409
2416 maxLength: 255, minLength: 1
2410 minLength: 1, maxLength: 255
24172411
24182412 - `timezone: optional string or null`
24192413
24202414 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
24212415
2422 maxLength: 255, minLength: 1
2416 minLength: 1, maxLength: 255
24232417
24242418 - `WebFetchTool20250910 object`
24252419
from line 2459
24652459
24662460 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
24672461
2468 exclusiveMinimum: 0
2462 minimum: 1
24692463
24702464 - `max_uses: optional number or null`
24712465
24722466 Maximum number of times the tool can be used in the API request.
24732467
2474 exclusiveMinimum: 0
2468 minimum: 1
24752469
24762470 - `strict: optional boolean`
24772471
from line 2473
24792473
24802474 - `url_sources: optional WebFetchURLSources or null`
24812475
2482 Which sources contribute to the set of URLs web fetch may fetch.
2476 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
24832477
2484 Each key is a tagged variant: `user_input` is `all` or `none`; the
2485 two tool filters are `all`, `none`, `only` (only the named tools'
2486 results) or `except` (every result but the named tools'). A named tool
2487 must be declared in this request's `tools[]`.
2488
24892478 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
24902479
24912480 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 2597
26082597
26092598 Maximum number of times the tool can be used in the API request.
26102599
2611 exclusiveMinimum: 0
2600 minimum: 1
26122601
26132602 - `strict: optional boolean`
26142603
from line 2651
26622651
26632652 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
26642653
2665 exclusiveMinimum: 0
2654 minimum: 1
26662655
26672656 - `max_uses: optional number or null`
26682657
26692658 Maximum number of times the tool can be used in the API request.
26702659
2671 exclusiveMinimum: 0
2660 minimum: 1
26722661
26732662 - `strict: optional boolean`
26742663
from line 2665
26762665
26772666 - `url_sources: optional WebFetchURLSources or null`
26782667
2679 Which sources contribute to the set of URLs web fetch may fetch.
2668 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
26802669
2681 Each key is a tagged variant: `user_input` is `all` or `none`; the
2682 two tool filters are `all`, `none`, `only` (only the named tools'
2683 results) or `except` (every result but the named tools'). A named tool
2684 must be declared in this request's `tools[]`.
2685
26862670 - `WebFetchTool20260309 object`
26872671
26882672 Web fetch tool with use_cache parameter for bypassing cached content.
from line 2713
27292713
27302714 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
27312715
2732 exclusiveMinimum: 0
2716 minimum: 1
27332717
27342718 - `max_uses: optional number or null`
27352719
27362720 Maximum number of times the tool can be used in the API request.
27372721
2738 exclusiveMinimum: 0
2722 minimum: 1
27392723
27402724 - `strict: optional boolean`
27412725
from line 2727
27432727
27442728 - `url_sources: optional WebFetchURLSources or null`
27452729
2746 Which sources contribute to the set of URLs web fetch may fetch.
2730 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
27472731
2748 Each key is a tagged variant: `user_input` is `all` or `none`; the
2749 two tool filters are `all`, `none`, `only` (only the named tools'
2750 results) or `except` (every result but the named tools'). A named tool
2751 must be declared in this request's `tools[]`.
2752
27532732 - `use_cache: optional boolean`
27542733
27552734 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 2773
27942773
27952774 Maximum number of times the tool can be used in the API request.
27962775
2797 exclusiveMinimum: 0
2776 minimum: 1
27982777
27992778 - `response_inclusion: optional "full" or "excluded"`
28002779
from line 2835
28562835
28572836 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
28582837
2859 exclusiveMinimum: 0
2838 minimum: 1
28602839
28612840 - `max_uses: optional number or null`
28622841
28632842 Maximum number of times the tool can be used in the API request.
28642843
2865 exclusiveMinimum: 0
2844 minimum: 1
28662845
28672846 - `response_inclusion: optional "full" or "excluded"`
28682847
from line 2857
28782857
28792858 - `url_sources: optional WebFetchURLSources or null`
28802859
2881 Which sources contribute to the set of URLs web fetch may fetch.
2882
2883 Each key is a tagged variant: `user_input` is `all` or `none`; the
2884 two tool filters are `all`, `none`, `only` (only the named tools'
2885 results) or `except` (every result but the named tools'). A named tool
2886 must be declared in this request's `tools[]`.
2860 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28872861
28882862 - `use_cache: optional boolean`
28892863
api/messages/create Changed · +179 / -197 lines
from line 139
139139
140140 - `document_title: string or null`
141141
142 maxLength: 500, minLength: 1
142 minLength: 1, maxLength: 500
143143
144144 - `end_char_index: number`
145145
from line 159
159159
160160 - `document_title: string or null`
161161
162 maxLength: 500, minLength: 1
162 minLength: 1, maxLength: 500
163163
164164 - `end_page_number: number`
165165
from line 183
183183
184184 - `document_title: string or null`
185185
186 maxLength: 500, minLength: 1
186 minLength: 1, maxLength: 500
187187
188188 - `end_block_index: number`
189189
from line 207
207207
208208 - `title: string or null`
209209
210 maxLength: 512, minLength: 1
210 minLength: 1, maxLength: 512
211211
212212 - `url: string`
213213
from line 363
363363
364364 - `title: optional string or null`
365365
366 maxLength: 500, minLength: 1
366 minLength: 1, maxLength: 500
367367
368368 - `SearchResultBlockParam object`
369369
from line 427
427427
428428 - `name: string`
429429
430 maxLength: 200, minLength: 1
430 minLength: 1, maxLength: 200
431431
432432 - `cache_control: optional CacheControlEphemeral or null`
433433
from line 463
463463
464464 For a toolset member tool_use, the toolset family this member belongs to.
465465
466 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
466 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
467467
468468 - `ToolResultBlockParam object`
469469
from line 499
499499
500500 - `tool_name: string`
501501
502 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
502 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
503503
504504 - `cache_control: optional CacheControlEphemeral or null`
505505
from line 527
527527
528528 The caller-assigned identifier for this tab, unique within the inventory.
529529
530 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
530 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
531531
532532 - `title: string`
533533
from line 553
553553
554554 Tabs opened and download state changes during this call. "Nothing to report" is expressed by omitting the field, never by an empty list.
555555
556 maxItems: 200, minItems: 1
556 minItems: 1, maxItems: 200
557557
558558 - `BrowserStateChangeTabOpened object`
559559
from line 571
571571
572572 The `tab_id` of the opened tab, present in `tabs`.
573573
574 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
574 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
575575
576576 - `BrowserStateChangeDownloadStarted object`
577577
from line 583
583583
584584 The caller-assigned identifier for this download, stable across the state changes reporting it.
585585
586 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
586 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
587587
588588 - `url: string`
589589
from line 604
604604
605605 The caller-assigned identifier for this download, stable across the state changes reporting it.
606606
607 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
607 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
608608
609609 - `url: string`
610610
from line 616
616616
617617 Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
618618
619 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
619 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
620620
621621 - `size_bytes: optional number or null`
622622
from line 634
634634
635635 The caller-assigned identifier for this download, stable across the state changes reporting it.
636636
637 maxLength: 4096, minLength: 1, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
637 minLength: 1, maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
638638
639639 - `url: string`
640640
from line 646
646646
647647 The failure or cancellation detail, when known.
648648
649 pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$, maxLength: 4096
649 maxLength: 4096, pattern: ^[^\x00-\x1f\x7f-\x9f\u2028\u2029]*$
650650
651651 - `is_error: optional boolean`
652652
from line 654
654654
655655 For a toolset member tool_result, the toolset family of the paired tool_use.
656656
657 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
657 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
658658
659659 - `ServerToolUseBlockParam object`
660660
from line 1032
10321032
10331033 - `tool_name: string`
10341034
1035 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
1035 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
10361036
10371037 - `cache_control: optional CacheControlEphemeral or null`
10381038
from line 1073
10731073
10741074 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
10751075
1076 - `string`
1077
10761078 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
10771079
10781080 The model that will complete your prompt.
from line 1117
11151117
11161118 Powerful intelligence for long-running agents and coding
11171119
1118 - `"claude-mythos-preview"`
1119
1120 New class of intelligence, strongest in coding and cybersecurity
1121
11221120 - `"claude-opus-4-6"`
11231121
11241122 Powerful intelligence for long-running agents and coding
from line 1149
11511149
11521150 High-performance model for agents and coding
11531151
1154 - `string`
1152 - `"claude-mythos-preview"`
11551153
1154 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
1155
1156 New class of intelligence, strongest in coding and cybersecurity
1157
11561158- `cache_control: optional CacheControlEphemeral or null`
11571159
11581160 Top-level cache control automatically applies a cache_control marker to the last cacheable block in the request.
from line 1189
11871189
11881190 Skill ID
11891191
1190 maxLength: 64, minLength: 1
1192 minLength: 1, maxLength: 64
11911193
11921194 - `version: optional string`
11931195
11941196 Skill version or 'latest' for most recent version
11951197
1196 maxLength: 64, minLength: 1
1198 minLength: 1, maxLength: 64
11971199
11981200 - `string`
11991201
12001202- `diagnostics: optional DiagnosticsParam or null`
12011203
1202 Request-level diagnostics. Currently carries the previous response
1203 id for prompt-cache divergence reporting.
1204 Request-level diagnostics. Supply `previous_message_id` to have the response include `diagnostics.cache_miss_reason` explaining any prompt-cache divergence from that prior request.
12041205
12051206 - `previous_message_id: optional string or null`
12061207
from line 1231
12301231
12311232 - `effort: optional "low" or "medium" or "high" or 2 more or null`
12321233
1233 All possible effort levels.
1234 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
12341235
1236 Valid values are `low`, `medium`, `high`, `xhigh`, or `max`.
1237
12351238 - `"low"`
12361239
12371240 - `"medium"`
from line 1483
14801483
14811484 This is how the tool will be called by the model and in `tool_use` blocks.
14821485
1483 maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
1486 minLength: 1, maxLength: 128, pattern: ^[a-zA-Z0-9_-]{1,128}$
14841487
14851488 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
14861489
from line 1700
16971700
16981701 - `configs: optional BrowserToolsetConfigs or null`
16991702
1700 Per-member configuration for `browser_toolset_20260801`: one
1701 optional field per member tool, keyed by the member name — the same
1702 name the member's `tool_use` blocks carry. Every member is an
1703 accepted key, and a member's defaults apply wherever its key is
1704 absent. Unknown keys are rejected: the field set is this toolset
1705 version's complete member set.
1703 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
17061704
17071705 - `type: optional BrowserTypeConfig or null`
17081706
from line 2127
21292127
21302128 - `configs: optional ComputerToolsetConfigs or null`
21312129
2132 Per-member configuration for `computer_toolset_20260801`: one
2133 optional field per member tool, keyed by the member name — the same
2134 name the member's `tool_use` blocks carry. Every member is an
2135 accepted key, and a member's defaults apply wherever its key is
2136 absent. Unknown keys are rejected: the field set is this toolset
2137 version's complete member set.
2130 Sparse per-member overrides, keyed by member name. Absent, null, and {} are equivalent; a member's defaults apply wherever its key is absent.
21382131
21392132 - `type: optional ComputerTypeConfig or null`
21402133
from line 2481
24882481
24892482 Maximum number of times the tool can be used in the API request.
24902483
2491 exclusiveMinimum: 0
2484 minimum: 1
24922485
24932486 - `strict: optional boolean`
24942487
from line 2497
25042497
25052498 The city of the user.
25062499
2507 maxLength: 255, minLength: 1
2500 minLength: 1, maxLength: 255
25082501
25092502 - `country: optional string or null`
25102503
25112504 The two letter [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1_alpha-2) of the user.
25122505
2513 maxLength: 2, minLength: 2
2506 minLength: 2, maxLength: 2
25142507
25152508 - `region: optional string or null`
25162509
25172510 The region of the user.
25182511
2519 maxLength: 255, minLength: 1
2512 minLength: 1, maxLength: 255
25202513
25212514 - `timezone: optional string or null`
25222515
25232516 The [IANA timezone](https://nodatime.org/TimeZones) of the user.
25242517
2525 maxLength: 255, minLength: 1
2518 minLength: 1, maxLength: 255
25262519
25272520 - `WebFetchTool20250910 object`
25282521
from line 2561
25682561
25692562 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
25702563
2571 exclusiveMinimum: 0
2564 minimum: 1
25722565
25732566 - `max_uses: optional number or null`
25742567
25752568 Maximum number of times the tool can be used in the API request.
25762569
2577 exclusiveMinimum: 0
2570 minimum: 1
25782571
25792572 - `strict: optional boolean`
25802573
from line 2575
25822575
25832576 - `url_sources: optional WebFetchURLSources or null`
25842577
2585 Which sources contribute to the set of URLs web fetch may fetch.
2578 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
25862579
2587 Each key is a tagged variant: `user_input` is `all` or `none`; the
2588 two tool filters are `all`, `none`, `only` (only the named tools'
2589 results) or `except` (every result but the named tools'). A named tool
2590 must be declared in this request's `tools[]`.
2591
25922580 - `client_tool_results: optional WebFetchURLSourceAll or WebFetchURLSourceNone or WebFetchURLSourceOnly or WebFetchURLSourceExcept`
25932581
25942582 Which client tools' results contribute fetchable URLs: "all", "none", or an only or except list of client tool names from tools[].
from line 2699
27112699
27122700 Maximum number of times the tool can be used in the API request.
27132701
2714 exclusiveMinimum: 0
2702 minimum: 1
27152703
27162704 - `strict: optional boolean`
27172705
from line 2753
27652753
27662754 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
27672755
2768 exclusiveMinimum: 0
2756 minimum: 1
27692757
27702758 - `max_uses: optional number or null`
27712759
27722760 Maximum number of times the tool can be used in the API request.
27732761
2774 exclusiveMinimum: 0
2762 minimum: 1
27752763
27762764 - `strict: optional boolean`
27772765
from line 2767
27792767
27802768 - `url_sources: optional WebFetchURLSources or null`
27812769
2782 Which sources contribute to the set of URLs web fetch may fetch.
2770 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
27832771
2784 Each key is a tagged variant: `user_input` is `all` or `none`; the
2785 two tool filters are `all`, `none`, `only` (only the named tools'
2786 results) or `except` (every result but the named tools'). A named tool
2787 must be declared in this request's `tools[]`.
2788
27892772 - `WebFetchTool20260309 object`
27902773
27912774 Web fetch tool with use_cache parameter for bypassing cached content.
from line 2815
28322815
28332816 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
28342817
2835 exclusiveMinimum: 0
2818 minimum: 1
28362819
28372820 - `max_uses: optional number or null`
28382821
28392822 Maximum number of times the tool can be used in the API request.
28402823
2841 exclusiveMinimum: 0
2824 minimum: 1
28422825
28432826 - `strict: optional boolean`
28442827
from line 2829
28462829
28472830 - `url_sources: optional WebFetchURLSources or null`
28482831
2849 Which sources contribute to the set of URLs web fetch may fetch.
2832 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
28502833
2851 Each key is a tagged variant: `user_input` is `all` or `none`; the
2852 two tool filters are `all`, `none`, `only` (only the named tools'
2853 results) or `except` (every result but the named tools'). A named tool
2854 must be declared in this request's `tools[]`.
2855
28562834 - `use_cache: optional boolean`
28572835
28582836 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 2875
28972875
28982876 Maximum number of times the tool can be used in the API request.
28992877
2900 exclusiveMinimum: 0
2878 minimum: 1
29012879
29022880 - `response_inclusion: optional "full" or "excluded"`
29032881
from line 2937
29592937
29602938 Maximum number of tokens used by including web page text content in the context. The limit is approximate and does not apply to binary content such as PDFs.
29612939
2962 exclusiveMinimum: 0
2940 minimum: 1
29632941
29642942 - `max_uses: optional number or null`
29652943
29662944 Maximum number of times the tool can be used in the API request.
29672945
2968 exclusiveMinimum: 0
2946 minimum: 1
29692947
29702948 - `response_inclusion: optional "full" or "excluded"`
29712949
from line 2959
29812959
29822960 - `url_sources: optional WebFetchURLSources or null`
29832961
2984 Which sources contribute to the set of URLs web fetch may fetch.
2962 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
29852963
2986 Each key is a tagged variant: `user_input` is `all` or `none`; the
2987 two tool filters are `all`, `none`, `only` (only the named tools'
2988 results) or `except` (every result but the named tools'). A named tool
2989 must be declared in this request's `tools[]`.
2990
29912964 - `use_cache: optional boolean`
29922965
29932966 Whether to use cached content. Set to false to bypass the cache and fetch fresh content. Only set to false when the user explicitly requests fresh content or when fetching rapidly-changing sources.
from line 3047
30743047
30753048 Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
30763049
3077 maximum: 1, minimum: 0
3050 minimum: 0, maximum: 1
30783051
30793052- `top_k: optional number`
30803053
from line 3071
30983071
30993072 Recommended for advanced use cases only.
31003073
3101 maximum: 1, minimum: 0
3074 minimum: 0, maximum: 1
31023075
31033076## Returns
31043077
from line 3093
31203093
31213094 - `container: Container or null`
31223095
3123 Information about the container used in the request (for the code execution tool)
3096 Information about the container used in this request.
31243097
3098 This will be non-null if a container tool (e.g. code execution) was used.
3099
31253100 - `id: string`
31263101
31273102 Identifier for the container used in this request
from line 3123
31483123
31493124 Skill ID
31503125
3151 maxLength: 64, minLength: 1
3126 minLength: 1, maxLength: 64
31523127
31533128 - `version: string`
31543129
31553130 The resolved version: a skill version ID for custom skills.
31563131
3157 maxLength: 64, minLength: 1
3132 minLength: 1, maxLength: 64
31583133
31593134 - `content: array of ContentBlock`
31603135
from line 3302
33273302
33283303 - `text: string`
33293304
3330 minLength: 0
3331
33323305 - `ThinkingBlock object`
33333306
33343307 - `type: "thinking"`
from line 3382
34093382
34103383 For a toolset member tool_use, the toolset family.
34113384
3412 maxLength: 64, minLength: 1, pattern: ^[a-zA-Z0-9_-]+$
3385 minLength: 1, maxLength: 64, pattern: ^[a-zA-Z0-9_-]+$
34133386
34143387 - `ServerToolUseBlock object`
34153388
from line 3830
38573830
38583831 - `tool_name: string`
38593832
3860 maxLength: 256, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,256}$
3833 minLength: 1, maxLength: 256, pattern: ^[a-zA-Z0-9_-]{1,256}$
38613834
38623835 - `tool_use_id: string`
38633836
from line 3848
38753848
38763849 - `diagnostics: Diagnostics or null`
38773850
3878 Request-level diagnostics: why the prompt cache could not fully reuse
3879 the prefix of the request named by `diagnostics.previous_message_id`.
3851 Request-level diagnostics. `null` when the request did not supply `diagnostics`, or when it did and no prompt-cache divergence was detected.
38803852
38813853 - `cache_miss_reason: CacheMissReason or null`
38823854
from line 3912
39403912
39413913 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
39423914
3915 - `string`
3916
39433917 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
39443918
39453919 The model that will complete your prompt.
from line 3956
39823956
39833957 Powerful intelligence for long-running agents and coding
39843958
3985 - `"claude-mythos-preview"`
3986
3987 New class of intelligence, strongest in coding and cybersecurity
3988
39893959 - `"claude-opus-4-6"`
39903960
39913961 Powerful intelligence for long-running agents and coding
from line 3988
40183988
40193989 High-performance model for agents and coding
40203990
4021 - `string`
3991 - `"claude-mythos-preview"`
40223992
3993 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
3994
3995 New class of intelligence, strongest in coding and cybersecurity
3996
40233997 - `role: "assistant"`
40243998
40253999 Conversational role of the generated message.
from line 4004
40304004
40314005 - `stop_details: RefusalStopDetails or null`
40324006
4033 Structured information about a refusal.
4007 Structured information about why model output stopped.
40344008
4009 This is `null` when the `stop_reason` has no additional detail to report.
4010
40354011 - `type: "refusal"`
40364012
40374013 default: refusal
from line 4014
40384014
40394015 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
40404016
4041 The policy category that triggered a refusal.
4017 The policy category that triggered the refusal.
40424018
4019 `null` when the refusal doesn't map to a named category.
4020
40434021 - `"cyber"`
40444022
40454023 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
from line 4204
42264204
42274205 - `container: Container or null`
42284206
4229 Information about the container used in the request (for the code execution tool)
4207 Information about the container used in this request.
42304208
4209 This will be non-null if a container tool (e.g. code execution) was used.
4210
42314211 - `stop_details: RefusalStopDetails or null`
42324212
4233 Structured information about a refusal.
4213 Structured information about why model output stopped.
4214
4215 This is `null` when the `stop_reason` has no additional detail to report.
42344216
42354217 - `stop_reason: StopReason or null`
42364218
api/models Changed · +24 / -24 lines
from line 29
2929
3030 Defaults to `20`. Ranges from `1` to `1000`.
3131
32 default: 20, maximum: 1000, minimum: 1
32 default: 20, minimum: 1, maximum: 1000
3333
3434### Headers
3535
from line 163
163163
164164 - `capabilities: ModelCapabilities or null`
165165
166 Model capability information.
166 Object mapping capability names to their support details. Keys are always present for all known capabilities.
167167
168168 - `batch: CapabilitySupport`
169169
from line 187
187187
188188 - `clear_thinking_20251015: CapabilitySupport or null`
189189
190 Indicates whether a capability is supported.
190 Whether the clear_thinking_20251015 strategy is supported.
191191
192192 - `clear_tool_uses_20250919: CapabilitySupport or null`
193193
194 Indicates whether a capability is supported.
194 Whether the clear_tool_uses_20250919 strategy is supported.
195195
196196 - `compact_20260112: CapabilitySupport or null`
197197
198 Indicates whether a capability is supported.
198 Whether the compact_20260112 strategy is supported.
199199
200200 - `supported: boolean`
201201
from line 227
227227
228228 - `xhigh: CapabilitySupport or null`
229229
230 Indicates whether a capability is supported.
230 Whether the model supports xhigh effort level.
231231
232232 - `image_input: CapabilitySupport`
233233
from line 526
526526
527527 - `capabilities: ModelCapabilities or null`
528528
529 Model capability information.
529 Object mapping capability names to their support details. Keys are always present for all known capabilities.
530530
531531 - `batch: CapabilitySupport`
532532
from line 550
550550
551551 - `clear_thinking_20251015: CapabilitySupport or null`
552552
553 Indicates whether a capability is supported.
553 Whether the clear_thinking_20251015 strategy is supported.
554554
555555 - `clear_tool_uses_20250919: CapabilitySupport or null`
556556
557 Indicates whether a capability is supported.
557 Whether the clear_tool_uses_20250919 strategy is supported.
558558
559559 - `compact_20260112: CapabilitySupport or null`
560560
561 Indicates whether a capability is supported.
561 Whether the compact_20260112 strategy is supported.
562562
563563 - `supported: boolean`
564564
from line 590
590590
591591 - `xhigh: CapabilitySupport or null`
592592
593 Indicates whether a capability is supported.
593 Whether the model supports xhigh effort level.
594594
595595 - `image_input: CapabilitySupport`
596596
from line 744
744744
745745 - `clear_thinking_20251015: CapabilitySupport or null`
746746
747 Indicates whether a capability is supported.
747 Whether the clear_thinking_20251015 strategy is supported.
748748
749749 - `supported: boolean`
750750
from line 752
752752
753753 - `clear_tool_uses_20250919: CapabilitySupport or null`
754754
755 Indicates whether a capability is supported.
755 Whether the clear_tool_uses_20250919 strategy is supported.
756756
757757 - `compact_20260112: CapabilitySupport or null`
758758
759 Indicates whether a capability is supported.
759 Whether the compact_20260112 strategy is supported.
760760
761761 - `supported: boolean`
762762
from line 794
794794
795795 - `xhigh: CapabilitySupport or null`
796796
797 Indicates whether a capability is supported.
797 Whether the model supports xhigh effort level.
798798
799799### Model Capabilities
800800
from line 824
824824
825825 - `clear_thinking_20251015: CapabilitySupport or null`
826826
827 Indicates whether a capability is supported.
827 Whether the clear_thinking_20251015 strategy is supported.
828828
829829 - `clear_tool_uses_20250919: CapabilitySupport or null`
830830
831 Indicates whether a capability is supported.
831 Whether the clear_tool_uses_20250919 strategy is supported.
832832
833833 - `compact_20260112: CapabilitySupport or null`
834834
835 Indicates whether a capability is supported.
835 Whether the compact_20260112 strategy is supported.
836836
837837 - `supported: boolean`
838838
from line 864
864864
865865 - `xhigh: CapabilitySupport or null`
866866
867 Indicates whether a capability is supported.
867 Whether the model supports xhigh effort level.
868868
869869 - `image_input: CapabilitySupport`
870870
from line 916
916916
917917 - `capabilities: ModelCapabilities or null`
918918
919 Model capability information.
919 Object mapping capability names to their support details. Keys are always present for all known capabilities.
920920
921921 - `batch: CapabilitySupport`
922922
from line 940
940940
941941 - `clear_thinking_20251015: CapabilitySupport or null`
942942
943 Indicates whether a capability is supported.
943 Whether the clear_thinking_20251015 strategy is supported.
944944
945945 - `clear_tool_uses_20250919: CapabilitySupport or null`
946946
947 Indicates whether a capability is supported.
947 Whether the clear_tool_uses_20250919 strategy is supported.
948948
949949 - `compact_20260112: CapabilitySupport or null`
950950
951 Indicates whether a capability is supported.
951 Whether the compact_20260112 strategy is supported.
952952
953953 - `supported: boolean`
954954
from line 980
980980
981981 - `xhigh: CapabilitySupport or null`
982982
983 Indicates whether a capability is supported.
983 Whether the model supports xhigh effort level.
984984
985985 - `image_input: CapabilitySupport`
986986
api/models/list Changed · +6 / -6 lines
from line 27
2727
2828 Defaults to `20`. Ranges from `1` to `1000`.
2929
30 default: 20, maximum: 1000, minimum: 1
30 default: 20, minimum: 1, maximum: 1000
3131
3232## Headers
3333
from line 161
161161
162162 - `capabilities: ModelCapabilities or null`
163163
164 Model capability information.
164 Object mapping capability names to their support details. Keys are always present for all known capabilities.
165165
166166 - `batch: CapabilitySupport`
167167
from line 185
185185
186186 - `clear_thinking_20251015: CapabilitySupport or null`
187187
188 Indicates whether a capability is supported.
188 Whether the clear_thinking_20251015 strategy is supported.
189189
190190 - `clear_tool_uses_20250919: CapabilitySupport or null`
191191
192 Indicates whether a capability is supported.
192 Whether the clear_tool_uses_20250919 strategy is supported.
193193
194194 - `compact_20260112: CapabilitySupport or null`
195195
196 Indicates whether a capability is supported.
196 Whether the compact_20260112 strategy is supported.
197197
198198 - `supported: boolean`
199199
from line 225
225225
226226 - `xhigh: CapabilitySupport or null`
227227
228 Indicates whether a capability is supported.
228 Whether the model supports xhigh effort level.
229229
230230 - `image_input: CapabilitySupport`
231231
api/models/retrieve Changed · +5 / -5 lines
from line 149
149149
150150 - `capabilities: ModelCapabilities or null`
151151
152 Model capability information.
152 Object mapping capability names to their support details. Keys are always present for all known capabilities.
153153
154154 - `batch: CapabilitySupport`
155155
from line 173
173173
174174 - `clear_thinking_20251015: CapabilitySupport or null`
175175
176 Indicates whether a capability is supported.
176 Whether the clear_thinking_20251015 strategy is supported.
177177
178178 - `clear_tool_uses_20250919: CapabilitySupport or null`
179179
180 Indicates whether a capability is supported.
180 Whether the clear_tool_uses_20250919 strategy is supported.
181181
182182 - `compact_20260112: CapabilitySupport or null`
183183
184 Indicates whether a capability is supported.
184 Whether the compact_20260112 strategy is supported.
185185
186186 - `supported: boolean`
187187
from line 213
213213
214214 - `xhigh: CapabilitySupport or null`
215215
216 Indicates whether a capability is supported.
216 Whether the model supports xhigh effort level.
217217
218218 - `image_input: CapabilitySupport`
219219
build-with-claude/batch-processing Changed · +3 / -3 lines
from line 446
446446
447447### Tracking your batch
448448
449The Message Batch's `processing_status` field indicates the stage of processing the batch is in. It starts as `in_progress`, then updates to `ended` once all the requests in the batch have finished processing, and results are ready. You can monitor the state of your batch by visiting the [Console](https://platform.claude.com/settings/workspaces/default/batches), or using the [retrieval endpoint](https://platform.claude.com/docs/en/api/retrieving-message-batches).
449The Message Batch's `processing_status` field indicates the stage of processing the batch is in. It starts as `in_progress`, then updates to `ended` once all the requests in the batch have finished processing, and results are ready. You can monitor the state of your batch by visiting the [Console](https://platform.claude.com/settings/workspaces/default/batches), or using the [retrieval endpoint](https://platform.claude.com/docs/en/api/messages/batches/retrieve).
450450
451451#### Polling for Message Batch completion
452452
from line 604
604604
605605### Listing all Message Batches
606606
607You can list all Message Batches in your Workspace using the [list endpoint](https://platform.claude.com/docs/en/api/listing-message-batches). The API supports pagination, automatically fetching additional pages as needed:
607You can list all Message Batches in your Workspace using the [list endpoint](https://platform.claude.com/docs/en/api/messages/batches/list). The API supports pagination, automatically fetching additional pages as needed:
608608
609609<CodeGroup>
610610 ```bash cURL
from line 950
950950
951951### Canceling a Message Batch
952952
953You can cancel a Message Batch that is currently processing using the [cancel endpoint](https://platform.claude.com/docs/en/api/canceling-message-batches). Immediately after cancellation, a batch's `processing_status` will be `canceling`. You can use the same polling technique described earlier to wait until cancellation is finalized. Canceled batches end up with a status of `ended` and may contain partial results for requests that were processed before cancellation.
953You can cancel a Message Batch that is currently processing using the [cancel endpoint](https://platform.claude.com/docs/en/api/messages/batches/cancel). Immediately after cancellation, a batch's `processing_status` will be `canceling`. You can use the same polling technique described earlier to wait until cancellation is finalized. Canceled batches end up with a status of `ended` and may contain partial results for requests that were processed before cancellation.
954954
955955<CodeGroup>
956956 ```bash cURL
build-with-claude/claude-on-amazon-bedrock-legacy Changed · +10 / -12 lines
from line 144
144144
145145To invoke these models, pass an inference profile instead of the base model ID. The inference profile ID is the base model ID with a prefix from a column marked "Yes" in the following table, for example us.anthropic.claude-sonnet-4-5-20250929-v1:0. You can also pass the full inference profile ARN, in the form `arn:aws:bedrock:{region}:{account-id}:inference-profile/{inference-profile-id}`. For AWS's authoritative list of available inference profiles, see [Supported Regions and models for inference profiles](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-support.html). To learn how the prefixes affect routing and pricing, see the [Global versus regional endpoints](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy#global-vs-regional-endpoints) section.
146146
147| Model | Base Bedrock model ID | `global` | `us` | `eu` | `jp` | `apac` |
148| ---------------------------- | ----------------------------------------- | -------- | ---- | ---- | ---- | ------ |
149| Claude Opus 4.6 | anthropic.claude-opus-4-6-v1 | Yes | Yes | Yes | Yes | Yes |
150| Claude Sonnet 4.6 | anthropic.claude-sonnet-4-6 | Yes | Yes | Yes | Yes | No |
151| Claude Sonnet 4.5 | anthropic.claude-sonnet-4-5-20250929-v1:0 | Yes | Yes | Yes | Yes | No |
152| Claude Sonnet 4 Deprecated. | anthropic.claude-sonnet-4-20250514-v1:0 | Yes | Yes | Yes | No | Yes |
153| Claude Sonnet 3.7 Retired. | anthropic.claude-3-7-sonnet-20250219-v1:0 | No | No | No | No | No |
154| Claude Opus 4.5 | anthropic.claude-opus-4-5-20251101-v1:0 | Yes | Yes | Yes | No | No |
155| Claude Opus 4.1 Deprecated. | anthropic.claude-opus-4-1-20250805-v1:0 | No | Yes | No | No | No |
156| Claude Opus 4 Retired. | anthropic.claude-opus-4-20250514-v1:0 | No | No | No | No | No |
157| Claude Haiku 4.5 | anthropic.claude-haiku-4-5-20251001-v1:0 | Yes | Yes | Yes | No | No |
158| Claude Haiku 3.5 Deprecated. | anthropic.claude-3-5-haiku-20241022-v1:0 | No | Yes | No | No | No |
147| Model | Base Bedrock model ID | `global` | `us` | `eu` | `jp` | `apac` |
148| :--------------------------------------------------------------------------------------------------- | :------------------------------------------ | :------- | :--- | :--- | :--- | :----- |
149| Claude Opus 4.6 | `anthropic.claude-opus-4-6-v1` | Yes | Yes | Yes | Yes | Yes |
150| Claude Opus 4.5 | `anthropic.claude-opus-4-5-20251101-v1:0` | Yes | Yes | Yes | No | No |
151| Claude Opus 4.1 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | `anthropic.claude-opus-4-1-20250805-v1:0` | No | Yes | No | No | No |
152| Claude Sonnet 4.6 | `anthropic.claude-sonnet-4-6` | Yes | Yes | Yes | Yes | No |
153| Claude Sonnet 4.5 | `anthropic.claude-sonnet-4-5-20250929-v1:0` | Yes | Yes | Yes | Yes | No |
154| Claude Sonnet 4 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | `anthropic.claude-sonnet-4-20250514-v1:0` | Yes | Yes | Yes | No | Yes |
155| Claude Haiku 4.5 | `anthropic.claude-haiku-4-5-20251001-v1:0` | Yes | Yes | Yes | No | No |
156| Claude Haiku 3.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | `anthropic.claude-3-5-haiku-20241022-v1:0` | No | Yes | No | No | No |
159157
160158### List available models
161159
build-with-claude/handling-stop-reasons Changed · +8 / -2 lines
from line 2394
23942394
23952395 for _ in range(max_continuations):
23962396 response = client.messages.create(
2397 model="claude-opus-5-5", max_tokens=4096, messages=messages, tools=tools
2397 model="claude-opus-5-5",
2398 max_tokens=4096,
2399 messages=messages,
2400 tools=tools,
23982401 )
23992402
24002403 if response.stop_reason != "pause_turn":
from line 3037
30343037
30353038 while True:
30363039 response = client.messages.create(
3037 model="claude-opus-5-5", max_tokens=1024, messages=messages, tools=tools
3040 model="claude-opus-5-5",
3041 max_tokens=1024,
3042 messages=messages,
3043 tools=tools,
30383044 )
30393045
30403046 if response.stop_reason == "tool_use":
build-with-claude/preserved-thinking Changed · +5 / -1 lines
from line 80
8080* **`"error"` (the default):** the API rejects the request with a 400 `invalid_request_error` that names the first failing block.
8181* **`"drop_block"`:** the API drops each failing block and every thinking block after it, and the request succeeds. Dropped blocks aren't billed. The model answers that turn without using reasoning from dropped blocks, and the prompt cache restarts at the edit. The response lists each dropped block in `input_transformations` (on the `message_start` event when streaming) with `reason: "prefix_binding_mismatch"`.
8282
83`"drop_block"` keeps requests succeeding but doesn't fix the edit. Count the responses in each session whose `input_transformations` has a `prefix_binding_mismatch` entry, and alert on them. In the Message Batches API, an item that leaves the field unset doesn't fail. Where the API enforces the check by default, it drops the failing blocks instead. Set `"error"` explicitly there if you want batch items to fail.
83<Warning>
84 `"drop_block"` hides the error but doesn't fix the edit that caused it. Dropped blocks aren't billed, but a session's token usage might still increase because Claude can sometimes think more to re-create the dropped thinking. The increase tends to be larger when more thinking blocks are dropped, or when blocks are dropped on more turns of a long session.
85</Warning>
86
87Count the responses in each session whose `input_transformations` has a `prefix_binding_mismatch` entry, alert on them, and replace each edit with the matching pattern in [Make changes without editing the prefix](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#replace-prefix-edits). In the Message Batches API, an item that leaves the field unset doesn't fail. Where the API enforces the check by default, it drops the failing blocks instead. Set `"error"` explicitly there if you want batch items to fail.
8488
8589Both the field and the `input_transformations` array require the `thinking-binding-controls-2026-08-01` [beta header](https://platform.claude.com/docs/en/api/beta-headers). [Set the mismatch behavior and read `input_transformations`](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#preserved-thinking-controls) shows the request in each SDK.
8690
build-with-claude/refusals-and-fallback Changed · +17 / -9 lines
from line 180
180180* `category` and `explanation` are both `null` when the refusal does not map to a named category. That `null` is a normal, permanent value, not a placeholder.
181181* `stop_details` itself is `null` for every stop reason other than `refusal`.
182182
183| `category` | What it means |
184| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
185| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. |
186| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. |
187| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. |
188| `"reasoning_extraction"` | The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). |
189| `"general_harms"` | The request falls under a usage-policy area outside the four named categories. Benign work can also trigger this category. |
183| `category` | What it means | Billed before any output |
184| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ |
185| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. | No |
186| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. | Yes |
187| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. | Yes |
188| `"reasoning_extraction"` | The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). | Yes |
189| `"general_harms"` | The request falls under a usage-policy area outside the four named categories. Benign work can also trigger this category. | No |
190190
191191A refusal can arrive before any output, or mid-stream after partial output. In either case, treat any partial output as incomplete and discard it.
192192
193193## How refusals are billed
194194
195You are not billed for a refusal that arrives before any output. `content` is empty, and token counts appear in `usage` but are not charged. The request still counts against your rate limits. A mid-stream refusal bills the input tokens and the output already streamed at normal rates.
195These billing rules apply on every platform: the Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.
196196
197**Refusals before any output:** To disrupt attempts to circumvent Anthropic's safeguards at scale, a refusal that arrives before any output is billed when its `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. These are the categories where Anthropic measures low volumes of false positives, as of September 2026. These refusals are billed like any other request, at the rates of the model that ran it. A refusal before any output in any other category, or with a `null` category, is not billed. Either way, `content` is empty and token counts appear in `usage`. The request still counts against your rate limits.
198
199**Mid-stream refusals:** A mid-stream refusal bills the input tokens and the output already streamed at normal rates.
200
201**Fallback:** When you use fallback, the refusal that triggered it is billed, in addition to the fallback request, when it arrived mid-stream or is in one of the billed categories. [Fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) compensates for the fallback request's prompt-cache miss, so you don't pay to cache the conversation twice. For how server-side fallback reports each attempt, see [Billing and rate limits](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#billing-and-rate-limits).
202
203The billed categories may change as Anthropic keeps measuring and refining its safeguards' false positive rates. The **Billed before any output** column in the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) lists the billed categories.
204
197205## Picking a fallback approach
198206
199207There are three ways to retry a refused request on another model. The right one depends on where you are running and how much control you need.
from line 745
737745
738746### Billing and rate limits
739747
740An attempt that declined before producing any output is not billed: its tokens are reported on its `usage.iterations` entry but not charged. Every attempt that produced output, including one that declined partway through its response, is billed separately at the rates of the model that ran it. The `usage.iterations` array is the per-attempt record of what you're billed. The top-level `usage` counts describe only the attempt that produced the returned message. Tokens from different models are never summed into one field.
748Each attempt follows the rules in [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed), at the rates of the model that ran it. An attempt that declined before producing any output is billed only when its refusal category is billed, and its tokens are reported on its `usage.iterations` entry either way. Every attempt that produced output, including one that declined partway through its response, is billed separately. The `usage.iterations` array is the per-attempt record of what you're billed. The top-level `usage` counts describe only the attempt that produced the returned message. Tokens from different models are never summed into one field.
741749
742750Every attempt that runs, including one that declined, counts against its own model's rate limits.
743751
cli-sdks-libraries/cli/apply Changed · +22 / -20 lines
from line 12
1212
1313Write the agent as a Markdown file under `agents/` and apply it:
1414
15<MultiFileExample language="cli" label="CLI">
16 ```bash CLI
17 ant apply agents/summarizer.md
18 ```
15<CodeGroup>
16 <CodeGroupItem>
17 ```bash CLI
18 ant apply agents/summarizer.md
19 ```
1920
20 <File filename="agents/summarizer.md">
21 ```markdown
22 ---
23 name: Summarizer
24 model: claude-opus-5-5
25 tools:
26 - type: agent_toolset_20260401
27 ---
21 <File filename="agents/summarizer.md">
22 ```markdown
23 ---
24 name: Summarizer
25 model: claude-opus-5-5
26 tools:
27 - type: agent_toolset_20260401
28 ---
2829
29 You are a helpful assistant that writes concise summaries.
30 ```
31 </File>
32</MultiFileExample>
30 You are a helpful assistant that writes concise summaries.
31 ```
32 </File>
33 </CodeGroupItem>
34</CodeGroup>
3335
3436The frontmatter holds the agent's configuration (the fields from [Define your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup)) and the body is its system prompt. `ant apply` [infers](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/apply#kind-inference) that the file is an agent from its path, here the `agents/` directory.
3537
from line 108
106108
107109Resources refer to each other by path. Wherever the API expects another resource's ID, write the relative path to that resource's file instead. In this project, the reviewer agent lists `../skills/pr-summary` under `skills`, the lead agent lists `./reviewer.md` in its roster, and the deployment names its agent, environment, and memory store by path. `ant apply` creates them in dependency order and fills in the real IDs. The project has six files:
108110
109<MultiFileExample variant="explorer">
111<FileExplorer>
110112 <File filename="agents/reviewer.md">
111113 ```markdown
112114 ---
from line 190
188190 Review any open pull requests. Start with the oldest.
189191 ```
190192 </File>
191</MultiFileExample>
193</FileExplorer>
192194
193195Apply the whole directory:
194196