Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

Batches changed

api/beta/messages/batches

Nearest release: v2.1.258, published an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+357added
Lines−31removed
From line 18 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits13to this page, all time

The whole hunk

from line 18, old and new numbered
/
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 18
1818 
1919 - `string`
2020 
21 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
21 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
2222 
2323 - `"message-batches-2024-09-24"`
2424 
from line 102
102102 
103103 - `"ce-user-management-2026-07-13"`
104104 
105 - `"mid-conversation-output-config-2026-07-01"`
106 
107 - `"thinking-binding-controls-2026-08-01"`
108 
109 - `"mid-conversation-system-clear-at-2026-08-21"`
110 
105111- `"anthropic-user-profile-id": optional string`
106112 
107113 The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored.
from line 1420
14141420 
14151421 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
14161422 
1417 - `"claude-sonnet-5" or "claude-fable-5" or "claude-mythos-5" or 12 more`
1423 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
14181424 
14191425 The model that will complete your prompt.
14201426 
14211427 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
14221428 
1429 - `"claude-fable-5-1"`
1430 
1431 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
1432 
1433 - `"claude-mythos-5-1"`
1434 
1435 Our most capable model for cybersecurity and biology research, available through trusted access programs
1436 
14231437 - `"claude-sonnet-5"`
14241438 
14251439 High-performance model for coding and agents
from line 1514
15001514 
15011515 - `"system"`
15021516 
1517 - `clear_at: optional "next_user_message" or "never" or null`
1518 
1519 How long this system message's text stays in front of the model. `"never"` (the default) renders it on every request that includes it. `"next_user_message"` renders it only for the user turn it follows: once a later `role: "user"` message exists in `messages` the message stays in the array (send it unchanged) but is no longer shown to the model. Only permitted on `role: "system"` messages.
1520 
1521 - `"next_user_message"`
1522 
1523 - `"never"`
1524 
1525 - `output_config: optional BetaSystemMessageOutputConfig or null`
1526 
1527 Per-message output configuration on a role:"system" input message.
1528 
1529 Fields here apply per-turn; `format` remains top-level only. An
1530 empty `{}` is accepted on a message that carries content; a message
1531 with neither content nor output_config fields is rejected.
1532 
1533 - `effort: optional "low" or "medium" or "high" or 2 more or null`
1534 
1535 All possible effort levels.
1536 
1537 - `"low"`
1538 
1539 - `"medium"`
1540 
1541 - `"high"`
1542 
1543 - `"xhigh"`
1544 
1545 - `"max"`
1546 
15031547 - `model: Model`
15041548 
15051549 The model that will complete your prompt.
from line 1846
18021846 
18031847 - `type: "enabled"`
18041848 
1849 - `block_binding: optional BetaThinkingBlockBinding or null`
1850 
1851 Controls for block binding: what happens when a thinking block this
1852 request sends back fails the conversation check. Every field is optional;
1853 an empty object means every default.
1854 
1855 - `prefix_mismatch_behavior: optional BetaThinkingPrefixMismatchBehavior or null`
1856 
1857 What happens when a thinking block in `messages` fails the conversation
1858 check: it was created in a different conversation, or the messages before
1859 it have changed since. `"error"` (the default) fails the request with a
1860 400 error. `"drop_block"` removes the failing blocks and the request
1861 proceeds; the model no longer sees the dropped reasoning.
1862 
1863 - `"error"`
1864 
1865 - `"drop_block"`
1866 
18051867 - `display: optional "summarized" or "omitted" or "updates" or null`
18061868 
18071869 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
from line 1882
18201882 
18211883 - `type: "adaptive"`
18221884 
1885 - `block_binding: optional BetaThinkingBlockBinding or null`
1886 
1887 Controls for block binding: what happens when a thinking block this
1888 request sends back fails the conversation check. Every field is optional;
1889 an empty object means every default.
1890 
18231891 - `display: optional "summarized" or "omitted" or "updates" or null`
18241892 
18251893 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
from line 2389
23212389 
23222390 - `type: "browser_toolset_20260801"`
23232391 
2324 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
2325 
2326 - `"direct"`
2327 
2328 - `"code_execution_20250825"`
2329 
2330 - `"code_execution_20260120"`
2331 
2332 - `"code_execution_20260521"`
2333 
23342392 - `cache_control: optional BetaCacheControlEphemeral or null`
23352393 
23362394 Create a cache control breakpoint at this content block.
from line 3015
29573015 
29583016 - `type: "computer_toolset_20260801"`
29593017 
2960 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
2961 
2962 - `"direct"`
2963 
2964 - `"code_execution_20250825"`
2965 
2966 - `"code_execution_20260120"`
2967 
2968 - `"code_execution_20260521"`
2969 
29703018 - `cache_control: optional BetaCacheControlEphemeral or null`
29713019 
29723020 Create a cache control breakpoint at this content block.
from line 4153
41054153 
41064154 - `string`
41074155 
4108 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
4156 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
41094157 
41104158 - `"message-batches-2024-09-24"`
41114159 
from line 4237
41894237 
41904238 - `"ce-user-management-2026-07-13"`
41914239 
4240 - `"mid-conversation-output-config-2026-07-01"`
4241 
4242 - `"thinking-binding-controls-2026-08-01"`
4243 
4244 - `"mid-conversation-system-clear-at-2026-08-21"`
4245 
41924246### Returns
41934247 
41944248- `BetaMessageBatch object`
from line 4419
43654419 
43664420 - `string`
43674421 
4368 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
4422 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
43694423 
43704424 - `"message-batches-2024-09-24"`
43714425 
from line 4503
44494503 
44504504 - `"ce-user-management-2026-07-13"`
44514505 
4506 - `"mid-conversation-output-config-2026-07-01"`
4507 
4508 - `"thinking-binding-controls-2026-08-01"`
4509 
4510 - `"mid-conversation-system-clear-at-2026-08-21"`
4511 
44524512### Returns
44534513 
44544514- `data: array of BetaMessageBatch`
from line 4694
46344694 
46354695 - `string`
46364696 
4637 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
4697 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
46384698 
46394699 - `"message-batches-2024-09-24"`
46404700 
from line 4778
47184778 
47194779 - `"ce-user-management-2026-07-13"`
47204780 
4781 - `"mid-conversation-output-config-2026-07-01"`
4782 
4783 - `"thinking-binding-controls-2026-08-01"`
4784 
4785 - `"mid-conversation-system-clear-at-2026-08-21"`
4786 
47214787### Returns
47224788 
47234789- `BetaMessageBatch object`
from line 4951
48854951 
48864952 - `string`
48874953 
4888 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
4954 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
48894955 
48904956 - `"message-batches-2024-09-24"`
48914957 
from line 5035
49695035 
49705036 - `"ce-user-management-2026-07-13"`
49715037 
5038 - `"mid-conversation-output-config-2026-07-01"`
5039 
5040 - `"thinking-binding-controls-2026-08-01"`
5041 
5042 - `"mid-conversation-system-clear-at-2026-08-21"`
5043 
49725044### Returns
49735045 
49745046- `BetaDeletedMessageBatch object`
from line 5100
50285100 
50295101 - `string`
50305102 
5031 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
5103 - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 41 more`
50325104 
50335105 - `"message-batches-2024-09-24"`
50345106 
from line 5184
51125184 
51135185 - `"ce-user-management-2026-07-13"`
51145186 
5187 - `"mid-conversation-output-config-2026-07-01"`
5188 
5189 - `"thinking-binding-controls-2026-08-01"`
5190 
5191 - `"mid-conversation-system-clear-at-2026-08-21"`
5192 
51155193### Returns
51165194 
51175195- `BetaMessageBatchIndividualResponse object`
from line 6133
60556133 
60566134 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
60576135 
6058 - `"claude-sonnet-5" or "claude-fable-5" or "claude-mythos-5" or 12 more`
6136 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
60596137 
60606138 The model that will complete your prompt.
60616139 
60626140 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
60636141 
6142 - `"claude-fable-5-1"`
6143 
6144 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
6145 
6146 - `"claude-mythos-5-1"`
6147 
6148 Our most capable model for cybersecurity and biology research, available through trusted access programs
6149 
60646150 - `"claude-sonnet-5"`
60656151 
60666152 High-performance model for coding and agents
from line 6878
67926878 
67936879 - `"fast"`
67946880 
6881 - `input_transformations: optional array of BetaThinkingDroppedInputTransformation or null`
6882 
6883 Changes the API made to the request's input before showing it to the model:
6884 one entry per change, in request order. Today the only entry type is
6885 `thinking_dropped` — a `thinking`, `redacted_thinking` or `connector_text`
6886 block from the request's `messages` that was removed from the prompt instead
6887 of being shown to the model because it failed a binding check. More entry
6888 types may be added over time; ignore types you do not recognize.
6889 
6890 Requires `anthropic-beta: thinking-binding-controls-2026-08-01`. Present on
6891 every such response from a model that supports extended thinking, as `[]`
6892 when nothing was changed; without the beta, blocks are removed all the same
6893 but nothing is reported. Removed blocks contribute nothing to
6894 `usage.input_tokens`. When streaming, the array is final in `message_start`;
6895 the final `message_delta` event carries it only when a server-side model
6896 fallback happened mid-stream, in which case it holds the serving model's
6897 entries and replaces the one in `message_start`.
6898 
6899 - `path: string`
6900 
6901 Where the removed block was in your request, as `messages.{i}.content.{j}`:
6902 `i` indexes the `messages` array you sent and `j` that message's `content`
6903 array — the same form error messages use.
6904 
6905 - `reason: "model_binding_mismatch" or "prefix_binding_mismatch" or "organization_binding_mismatch" or "end_user_binding_mismatch"`
6906 
6907 Which binding check removed the block: `model_binding_mismatch` — it was
6908 created by a model whose reasoning the requested model may not read;
6909 `prefix_binding_mismatch` — the conversation before it differs from the
6910 conversation it was created in (the rest of that turn's consecutive thinking
6911 blocks are removed with it, each with this reason);
6912 `organization_binding_mismatch` — it was created under a different
6913 organization (an Anthropic organization, AWS account or Google Cloud project)
6914 and this organization is not one of its additional organizations;
6915 `end_user_binding_mismatch` — it was created for a different end user, or
6916 was removed by the consumer-organization binding. A block that would fail
6917 several checks reports one reason, in this order of precedence:
6918 `organization_binding_mismatch`, `end_user_binding_mismatch`,
6919 `model_binding_mismatch`, `prefix_binding_mismatch`.
6920 
6921 - `"model_binding_mismatch"`
6922 
6923 - `"prefix_binding_mismatch"`
6924 
6925 - `"organization_binding_mismatch"`
6926 
6927 - `"end_user_binding_mismatch"`
6928 
6929 - `type: "thinking_dropped"`
6930 
6931 Always `thinking_dropped` for this entry type.
6932 
6933 default: thinking_dropped
6934 
67956935 - `type: "succeeded"`
67966936 
67976937 default: succeeded
from line 8258
81188258 
81198259 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
81208260 
8121 - `"claude-sonnet-5" or "claude-fable-5" or "claude-mythos-5" or 12 more`
8261 - `"claude-fable-5-1" or "claude-mythos-5-1" or "claude-sonnet-5" or 14 more`
81228262 
81238263 The model that will complete your prompt.
81248264 
81258265 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
81268266 
8267 - `"claude-fable-5-1"`
8268 
8269 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
8270 
8271 - `"claude-mythos-5-1"`
8272 
8273 Our most capable model for cybersecurity and biology research, available through trusted access programs
8274 
81278275 - `"claude-sonnet-5"`
81288276 
81298277 High-performance model for coding and agents
from line 8336
81888336 
81898337 - `to: BetaFallbackInfo`
81908338 
8191 The fallback model producing the content that follows this block. Its `model` is always the canonical id.
8192 
8193 - `trigger: BetaFallbackRefusalTrigger`
8194 
8195 What caused the `from` model to hand over at this hop.
8196 
8197 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
8198 
8199 The policy category that triggered a refusal.
8200 
8201 - `"cyber"`
8202 
8203 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
8204 
8205 - `"bio"`
8206 
8207 The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.
8208 
8209 - `"frontier_llm"`
8210 
8211 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.
8212 
8213 - `"reasoning_extraction"`
8214 
8215 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/adaptive-thinking).
8216 
8217 - `"general_harms"`
8218 
8219 The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category.
8220 
8221 - `type: "refusal"`
8222 
8223 default: refusal
8224 
8225 - `type: "fallback"`
8226 
8227 default: fallback
8228 
8229 - `context_management: BetaContextManagementResponse or null`
8230 
8231 Context management response.
8232 
8233 Information about context management strategies applied during the request.
8234 
8235 - `applied_edits: array of BetaClearToolUses20250919EditResponse or BetaClearThinking20251015EditResponse`
8236 
8237 List of context management edits that were applied.
8238 
8239 - `BetaClearToolUses20250919EditResponse object`
8240 
8241 - `cleared_input_tokens: number`
8242 
8243 Number of input tokens cleared by this edit.
8244 
8245 minimum: 0
8246 
8247 - `cleared_tool_uses: number`
8248 
8249 Number of tool uses that were cleared.
8250 
8251 minimum: 0
8252 
8253 - `type: "clear_tool_uses_20250919"`
8254 
8255 The type of context management edit applied.
8256 
8257 default: clear_tool_uses_20250919
8258 
8259 - `BetaClearThinking20251015EditResponse object`
8260 
8261 - `cleared_input_tokens: number`
8262 
8263 Number of input tokens cleared by this edit.
8264 
8265 minimum: 0
8266 
8267 - `cleared_thinking_turns: number`
8268 
8269 Number of thinking turns that were cleared.
8270 
8271 minimum: 0
8272 
8273 - `type: "clear_thinking_20251015"`
8274 
8275 The type of context management edit applied.
8276 
8277 default: clear_thinking_20251015
8278 
8279 - `diagnostics: BetaDiagnostics or null`
8280 
8281 Response envelope for request-level diagnostics. Present (possibly
8282 null) whenever the caller supplied `diagnostics` on the request.
8283 
8284 - `cache_miss_reason: BetaCacheMissModelChanged or BetaCacheMissSystemChanged or BetaCacheMissToolsChanged or 3 more or null`
8285 
8286 Explains why the prompt cache could not fully reuse the prefix from the request identified by `diagnostics.previous_message_id`. `null` means diagnosis is still pending — the response was serialized before the background comparison completed.
8287 
8288 - `BetaCacheMissModelChanged object`
8289 
8290 - `cache_missed_input_tokens: number`
8291 
8292 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8293 
8294 - `type: "model_changed"`
8295 
8296 default: model_changed
8297 
8298 - `BetaCacheMissSystemChanged object`
8299 
8300 - `cache_missed_input_tokens: number`
8301 
8302 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8303 
8304 - `type: "system_changed"`
8305 
8306 default: system_changed
8307 
8308 - `BetaCacheMissToolsChanged object`
8309 
8310 - `cache_missed_input_tokens: number`
8311 
8312 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8313 
8314 - `type: "tools_changed"`
8315 
8316 default: tools_changed
8317 
8318 - `BetaCacheMissMessagesChanged object`
8319 
8320 - `cache_missed_input_tokens: number`
8321 
8322 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8323 
8324 - `type: "messages_changed"`
8325 
8326 default: messages_changed
8327 
8328 - `BetaCacheMissPreviousMessageNotFound object`
8329 
8330 - `type: "previous_message_not_found"`
8331 
8332 default: previous_message_not_found
8333 
8334 - `BetaCacheMissUnavailable object`
8335 
8336 - `type: "unavailable"`
8337 
8338 default: unavailable
8339 
8340 - `model: Model`
8341 
8342 The model that will complete your prompt.
8343 
8344 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
8345 
8346 - `role: "assistant"`
8347 
8348 Conversational role of the generated message.
8349 
8350 This will always be `"assistant"`.
8351 
8352 default: assistant
8353 
8354 - `stop_details: BetaRefusalStopDetails or null`
8355 
8356 Structured information about a refusal.
8357 
8358 - `category: "cyber" or "bio" or "frontier_llm" or 2 more or null`
8359 
8360 The policy category that triggered a refusal.
8361 
8362 - `"cyber"`
8363 
8364 The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
8365 
8366 - `"bio"`
8367 
8368 The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.
8369 
8370 - `"frontier_llm"`
8371 
8372 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.
8373 
8374 - `"reasoning_extraction"`
8375 
8376 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/adaptive-thinking
8339 The fallback model produ