Follow Discord
Sweep 25 Sep 2026 · 19:33Z Build v2.1.283 504 read Stable v2.1.274 Latest v2.1.283 Next v2.1.283 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

Batches changedapi/messages/batches

Nearest release: v2.1.282, published an hour before 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+255added
Lines−0removed
From line 1,218 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 1218, 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.

The two sides of this change are more than 400 edits apart, too far apart to line up, so this is the differ's own diff of it and the words inside a line are not marked.

from line 1218
12181218 maxLength: 64, minLength: 1
12191219 
12201220 - `string`
1221 
1222 - `diagnostics: optional DiagnosticsParam or null`
1223 
1224 Request-level diagnostics. Currently carries the previous response
1225 id for prompt-cache divergence reporting.
1226 
1227 - `previous_message_id: optional string or null`
1228 
1229 The `id` (`msg_...`) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns `diagnostics.cache_miss_reason` when the prompt-cache prefix could not be reused. Pass `null` on the first turn to opt in without a prior message to compare.
1230 
1231 maxLength: 256
12211232 
12221233 - `inference_geo: optional string or null`
12231234 
from line 4681
46704681 
46714682 - `file_id: string`
46724683 
4684 - `diagnostics: Diagnostics or null`
4685 
4686 Request-level diagnostics: why the prompt cache could not fully reuse
4687 the prefix of the request named by `diagnostics.previous_message_id`.
4688 
4689 - `cache_miss_reason: CacheMissReason or null`
4690 
4691 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.
4692 
4693 - `CacheMissModelChanged object`
4694 
4695 - `type: "model_changed"`
4696 
4697 default: model_changed
4698 
4699 - `cache_missed_input_tokens: number`
4700 
4701 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
4702 
4703 - `CacheMissSystemChanged object`
4704 
4705 - `type: "system_changed"`
4706 
4707 default: system_changed
4708 
4709 - `cache_missed_input_tokens: number`
4710 
4711 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
4712 
4713 - `CacheMissToolsChanged object`
4714 
4715 - `type: "tools_changed"`
4716 
4717 default: tools_changed
4718 
4719 - `cache_missed_input_tokens: number`
4720 
4721 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
4722 
4723 - `CacheMissMessagesChanged object`
4724 
4725 - `type: "messages_changed"`
4726 
4727 default: messages_changed
4728 
4729 - `cache_missed_input_tokens: number`
4730 
4731 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
4732 
4733 - `CacheMissPreviousMessageNotFound object`
4734 
4735 - `type: "previous_message_not_found"`
4736 
4737 default: previous_message_not_found
4738 
4739 - `CacheMissUnavailable object`
4740 
4741 - `type: "unavailable"`
4742 
4743 default: unavailable
4744 
46734745 - `model: Model`
46744746 
46754747 The model that will complete your prompt.
from line 6187
61156187 
61166188 - `file_id: string`
61176189 
6190 - `diagnostics: Diagnostics or null`
6191 
6192 Request-level diagnostics: why the prompt cache could not fully reuse
6193 the prefix of the request named by `diagnostics.previous_message_id`.
6194 
6195 - `cache_miss_reason: CacheMissReason or null`
6196 
6197 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.
6198 
6199 - `CacheMissModelChanged object`
6200 
6201 - `type: "model_changed"`
6202 
6203 default: model_changed
6204 
6205 - `cache_missed_input_tokens: number`
6206 
6207 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
6208 
6209 - `CacheMissSystemChanged object`
6210 
6211 - `type: "system_changed"`
6212 
6213 default: system_changed
6214 
6215 - `cache_missed_input_tokens: number`
6216 
6217 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
6218 
6219 - `CacheMissToolsChanged object`
6220 
6221 - `type: "tools_changed"`
6222 
6223 default: tools_changed
6224 
6225 - `cache_missed_input_tokens: number`
6226 
6227 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
6228 
6229 - `CacheMissMessagesChanged object`
6230 
6231 - `type: "messages_changed"`
6232 
6233 default: messages_changed
6234 
6235 - `cache_missed_input_tokens: number`
6236 
6237 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
6238 
6239 - `CacheMissPreviousMessageNotFound object`
6240 
6241 - `type: "previous_message_not_found"`
6242 
6243 default: previous_message_not_found
6244 
6245 - `CacheMissUnavailable object`
6246 
6247 - `type: "unavailable"`
6248 
6249 default: unavailable
6250 
61186251 - `model: Model`
61196252 
61206253 The model that will complete your prompt.
from line 7465
73327465 
73337466 - `file_id: string`
73347467 
7468 - `diagnostics: Diagnostics or null`
7469 
7470 Request-level diagnostics: why the prompt cache could not fully reuse
7471 the prefix of the request named by `diagnostics.previous_message_id`.
7472 
7473 - `cache_miss_reason: CacheMissReason or null`
7474 
7475 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.
7476 
7477 - `CacheMissModelChanged object`
7478 
7479 - `type: "model_changed"`
7480 
7481 default: model_changed
7482 
7483 - `cache_missed_input_tokens: number`
7484 
7485 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
7486 
7487 - `CacheMissSystemChanged object`
7488 
7489 - `type: "system_changed"`
7490 
7491 default: system_changed
7492 
7493 - `cache_missed_input_tokens: number`
7494 
7495 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
7496 
7497 - `CacheMissToolsChanged object`
7498 
7499 - `type: "tools_changed"`
7500 
7501 default: tools_changed
7502 
7503 - `cache_missed_input_tokens: number`
7504 
7505 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
7506 
7507 - `CacheMissMessagesChanged object`
7508 
7509 - `type: "messages_changed"`
7510 
7511 default: messages_changed
7512 
7513 - `cache_missed_input_tokens: number`
7514 
7515 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
7516 
7517 - `CacheMissPreviousMessageNotFound object`
7518 
7519 - `type: "previous_message_not_found"`
7520 
7521 default: previous_message_not_found
7522 
7523 - `CacheMissUnavailable object`
7524 
7525 - `type: "unavailable"`
7526 
7527 default: unavailable
7528 
73357529 - `model: Model`
73367530 
73377531 The model that will complete your prompt.
from line 8695
85018695 
85028696 - `file_id: string`
85038697 
8698 - `diagnostics: Diagnostics or null`
8699 
8700 Request-level diagnostics: why the prompt cache could not fully reuse
8701 the prefix of the request named by `diagnostics.previous_message_id`.
8702 
8703 - `cache_miss_reason: CacheMissReason or null`
8704 
8705 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.
8706 
8707 - `CacheMissModelChanged object`
8708 
8709 - `type: "model_changed"`
8710 
8711 default: model_changed
8712 
8713 - `cache_missed_input_tokens: number`
8714 
8715 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8716 
8717 - `CacheMissSystemChanged object`
8718 
8719 - `type: "system_changed"`
8720 
8721 default: system_changed
8722 
8723 - `cache_missed_input_tokens: number`
8724 
8725 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8726 
8727 - `CacheMissToolsChanged object`
8728 
8729 - `type: "tools_changed"`
8730 
8731 default: tools_changed
8732 
8733 - `cache_missed_input_tokens: number`
8734 
8735 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8736 
8737 - `CacheMissMessagesChanged object`
8738 
8739 - `type: "messages_changed"`
8740 
8741 default: messages_changed
8742 
8743 - `cache_missed_input_tokens: number`
8744 
8745 Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
8746 
8747 - `CacheMissPreviousMessageNotFound object`
8748 
8749 - `type: "previous_message_not_found"`
8750 
8751 default: previous_message_not_found
8752 
8753 - `CacheMissUnavailable object`
8754 
8755 - `type: "unavailable"`
8756 
8757 default: unavailable
8758 
85048759 - `model: Model`
85058760 
85068761 The model that will complete your prompt.
85078762 
Feedback