One read of Claude Developer Platformapi-20261029T173726Z
320 pages moved out of 826 read.
Pages moved
320
significant first
Pages read
826
in this capture
Captured
17:37 UTC
Corpus hash
1b6c4dd3baa9
corpus-hash
What this read moved
1-25 of 320, page 1 of 13This capture is too large to show at once. Changes 1-25 of 320 are below, significant first; the rest are on the following screens.
about-claude/models/optimizing-for-cost-and-intelligence Changed · +4 / -4 lines
from line 196
196196 
197197</Frame>
198198
199At list prices, the stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break re-writes the prefix at 1.25x the input price instead of reading it at 0.025x. On Claude Haiku 5.5 a system prompt edit costs 12.5 times an unchanged request. The edit re-wrote the whole conversation. By default, newer accounts get a 400 error instead, except on Claude Mythos 5.1[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs). The top-level effort change, in a conversation that held the model’s first reply with its thinking, re-wrote all but the system prompt. These figures are from the Messages API.
199At list prices, the stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break rewrites the prefix at 1.25x the input price instead of reading it at 0.025x. On Claude Haiku 5.5, a system prompt edit cost 12.5x as much as an unchanged request, because the edit rewrote the whole conversation. On models that run the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), a request that makes this edit and sends earlier thinking blocks back can get a 400 error instead[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs). The top-level effort change, in a conversation that held the model’s first reply with its thinking, rewrote all but the system prompt. These figures are from the Messages API.
200200
201201**What to do.**
202202
from line 272
272272* Run-wide, the prune and context editing cache about equally well. If you use context editing, [clear in a few large batches](https://platform.claude.com/docs/en/build-with-claude/context-editing#context-editing-and-prompt-caching).
273273
274274<Note>
275 On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, rewriting an earlier tool result [invalidates every thinking block after it](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), so use compaction instead. The prune was measured on an earlier model without [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking); on these four models, [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) and [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) run on the server and don’t invalidate thinking blocks. [Send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned): dropping their thinking blocks costs output tokens on every turn, because Claude [re-creates the reasoning](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#drop-block-cost).
275 On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, rewriting an earlier tool result [invalidates every thinking block after it](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check), so use compaction instead. The prune was measured on an earlier model without [preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking); on these models, [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editing) and [compaction](https://platform.claude.com/docs/en/build-with-claude/compaction) run on the server and don’t invalidate thinking blocks. [Send assistant turns back exactly as returned](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#append-assistant-turns-exactly-as-returned): dropping their thinking blocks costs output tokens on every turn, because Claude [re-creates the reasoning](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#drop-block-cost).
276276</Note>
277277
278278The prune, adapted from the triage agent’s code:
from line 659
6596593. If the curve shows a gap effort can’t close, add the multi-model strategy that fits and re-run the suite.
6606604. Run the winner in shadow on a traffic slice before cutover, then keep the suite running.
661661
662**How to price a task.** Price each of the five token counts in a response’s `usage` at its own rate: uncached input, 5-minute and 1-hour cache writes at 1.25x and 2x the input price, cache reads, and output. Sum them across the task’s requests (the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api) reports the aggregate). On Claude Haiku 5.5, use the rates for each request’s prompt length, counting cache reads and writes (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)). When `usage.speed` is `"fast"`, use the [fast mode rates](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing).
662**How to price a task.** Price each of the five token counts in a response’s `usage` at its own rate: uncached input, 5-minute and 1-hour cache writes at 1.25x and 2x the input price, cache reads, and output. Sum them across the task’s requests (the [Usage and Cost Analytics API](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api) reports the aggregate). On Claude Haiku 5.5, use the rates for each request’s prompt length, counting cache reads and writes (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)). When `usage.speed` is `"fast"`, use the [fast mode rates](https://platform.claude.com/docs/en/about-claude/pricing#fast-mode-pricing).
663663
664664The following example computes one request’s cost at Claude Opus 5.5’s list prices. Change the three prices for another model:
665665
from line 1033
10331033
10341034 * **October 2026 test, one change to a long conversation:** Measured October 20, 2026, on Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, on the Messages API with no tools, adaptive thinking, each model’s default effort, the 5-minute cache, a cache breakpoint on the system prompt, and [automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching). The conversation held about 101,000 tokens: a 20,000-token system prompt, 13 user turns of filler text, the model’s own reply to the first turn with its thinking block, and one-word replies to the rest. Once one request had cached the conversation, a second added one short turn, and each measured request sent that longer conversation with one change. Two conversations per model gave the same result.
10351035 * **October 2026 test, tokens read and written:** With no change, and with a per-message effort change, the request read all 101,000 tokens and wrote none. With a 25-token mid-conversation system message, or a 25-token status line at the end of the newest user turn, it read them all and wrote only the new text. A top-level effort change (to `low` on Claude Fable 5.1 and Claude Sonnet 5.5, to `high` on Claude Opus 5.5 and Claude Haiku 5.5) read the 20,000-token system prompt and wrote 81,000 tokens. The same 25 tokens at the front or the end of the system prompt read nothing and wrote all 101,000. The request after a mid-conversation system message, a top-level effort change, or 25 tokens added to the end of the system prompt read the new prefix; a new status line at the front wrote everything again. A further test on October 21, 2026, on the same four models with conversations of 5,000 tokens, and on all but Claude Fable 5.1 with conversations of 100,000 tokens, all with one-word replies, sent a beta header for the first time mid-conversation, as a first per-message effort change may: that request read everything the request before it had cached, all 54 times. A system message sent with no beta header did the same, all 15 times.
1036 * **October 2026 test, how priced:** The chart gives the prompt side of one request, from its `usage` fields at list prices. The chart’s values, in the order system prompt edit, system message, top-level effort change, and per-message effort change: Claude Fable 5.1 $1.26 USD, $0.026 USD, $1.02 USD, and $0.025 USD; Claude Opus 5.5 $0.50 USD, $0.020 USD, $0.41 USD, and $0.020 USD; Claude Sonnet 5.5 $0.25 USD, $0.010 USD, $0.20 USD, and $0.010 USD. The unchanged request repeated an earlier request byte for byte; a new turn of about 25 tokens adds under $0.001 USD. On Claude Haiku 5.5, whose requests were over 100,000 prompt tokens and so at its [long context prices](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing): $0.063 USD for the system prompt edit, $0.052 USD for the effort change, and $0.005 USD for the read. The requests ran on an Anthropic-internal organization whose usage is metered the same way as a customer organization’s, and on which the API does not enforce the [prefix check](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check) by default, so its system prompt edits were accepted. On accounts created on or after August 31, 2026, 00:00 UTC, a request to one of these four models that sends earlier thinking blocks back gets a 400 error by default if it changes `system`, `tools`, or a message before one of them.
1036 * **October 2026 test, how priced:** The chart gives the prompt side of one request, from its `usage` fields at list prices. The chart’s values, in the order system prompt edit, system message, top-level effort change, and per-message effort change: Claude Fable 5.1 $1.26 USD, $0.026 USD, $1.02 USD, and $0.025 USD; Claude Opus 5.5 $0.50 USD, $0.020 USD, $0.41 USD, and $0.020 USD; Claude Sonnet 5.5 $0.25 USD, $0.010 USD, $0.20 USD, and $0.010 USD. The unchanged request repeated an earlier request byte for byte; a new turn of about 25 tokens adds under $0.001 USD. On Claude Haiku 5.5, whose requests were over 100,000 prompt tokens and so at its [long context prices](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing): $0.063 USD for the system prompt edit, $0.052 USD for the effort change, and $0.005 USD for the read. The requests ran on an Anthropic-internal organization whose usage is metered the same way as a customer organization’s. For that organization, the API lets failing thinking blocks through when a request leaves `prefix_mismatch_behavior` unset, so the system prompt edits in these tests were accepted. On an account created on or after August 31, 2026, 00:00 UTC, the same edit gets a 400 error on all four models, because each request sends an earlier thinking block back.
10371037 * **What was measured:** The triage agent’s long variant from [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens), run August 24, 2026, on Claude Sonnet 5 with the 5-minute cache, cost from the usage fields at list prices, five sessions per arm: a no-change arm at the default effort throughout ($0.81 USD per session), and two arms that start at low effort and make the same two cache-breaking changes, a switch to the default effort and one added tool, either mid-session at requests 12 and 17 ($0.95 USD) or together on the first request after the first compaction ($0.75 USD).
10381038 * **Fourth arm:** A fourth arm of six sessions, run August 25, 2026, made the same two changes on the request that triggered the first compaction ($0.92 USD per session): that request’s summarization pass wrote the 81,000-token context to the cache instead of reading it, so that pass cost $0.21 USD against $0.04 USD for the same pass in the boundary arm.
10391039 * **Compaction:** Sessions first compacted at request 21 to 25 (16 of the 21 sessions at request 22), once the prompt passed the 80,000-token compaction trigger, and two no-change sessions compacted a second time near the end. The boundary arm’s lower total than the no-change arm reflects its low-effort requests before the change and those second compactions rather than caching: the two arms’ re-write costs differ by under $0.01 USD.
agents-and-tools/tool-use/computer-use-tool Changed · +3 / -3 lines
from line 1827
18271827
18281828### Manage screenshot history
18291829
1830Long agent loops accumulate screenshots quickly (roughly 1,000–1,800 input tokens each). The API’s [request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits) also apply. Once a single request carries more than 20 images, every image in it is held to a stricter per-side limit. A loop that keeps its screenshot history reaches that count within a few dozen turns, so either resize each screenshot so that neither side exceeds 2000 px or prune older screenshots to keep 20 or fewer in the request.
1830Long agent loops accumulate screenshots quickly (roughly 1,000–1,800 input tokens each). The API’s [request limits](https://platform.claude.com/docs/en/build-with-claude/vision#request-limits) also apply. Once a single request carries more than 20 images, every image in it is held to a stricter per-side limit. A loop that keeps its screenshot history reaches that count within a few dozen turns, so either resize each screenshot to stay under that limit or prune older screenshots to keep 20 or fewer in the request.
18311831
18321832To keep [Prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching) effective while bounding context:
18331833
18341834* Place one `cache_control` breakpoint after the system prompt and tool definitions, and up to three more on the last `tool_result` block of each of the most recent turns, advancing them each turn. Within a [batch action](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#batch-actions), markers on several blocks act as a single breakpoint, but each still counts toward the limit of four, so use at most one in any turn.
1835* Prune old screenshots in *batches*, not one each turn. Dropping a screenshot every turn changes the prefix every turn and invalidates the cache. A reasonable default is to keep the last three screenshots and prune every 25 turns, so the prefix stays byte-identical between prune events; if your screenshots exceed 2000 px on either side, choose an interval that keeps each request at 20 or fewer images.
1836* On Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, avoid pruning on the client: removing an earlier screenshot [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in every request that still carries those turns. Resize screenshots to 2000 px or less per side instead, and use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context. If you must prune, keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on; after each prune, Claude continues without the thinking produced since the pruned screenshot, on that request and every later one. On Claude Sonnet 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With `between_tools`, keep the history append-only, or strip the thinking blocks from the edited turn on. On Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`; with `thinking: {"type": "disabled"}`, keep the history append-only, or strip the thinking blocks from the edited turn on.
1835* Prune old screenshots in *batches*, not one each turn. Dropping a screenshot every turn changes the prefix every turn and invalidates the cache. A reasonable default is to keep the last three screenshots and prune every 25 turns, so the prefix stays byte-identical between prune events; if your screenshots exceed the stricter limit, choose an interval that keeps each request at 20 or fewer images.
1836* On Claude Fable 5.1, Claude Mythos 5.1, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5, avoid pruning on the client: removing an earlier screenshot from a request [invalidates every later thinking block](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-in-conversation) in that request and in every later request. Resize screenshots to stay under the stricter limit instead and use server-side [tool result clearing](https://platform.claude.com/docs/en/build-with-claude/context-editing#tool-result-clearing) to drop old ones from the context. If you must prune, keep [`prefix_mismatch_behavior: "drop_block"`](https://platform.claude.com/docs/en/build-with-claude/thinking#preserved-thinking-controls) set from then on; after each prune, Claude continues without the thinking produced since the pruned screenshot, on that request and every later one. On Claude Sonnet 5.5 and Claude Haiku 5.5, `block_binding` works only with `thinking: {"type": "adaptive"}`. With any other thinking setting on those models, keep the history append-only or strip every `thinking` and `redacted_thinking` block after the pruned screenshot.
18371837
18381838### Diagnose click issues
18391839
api/beta Changed · +2405 / -33 lines
## Beta › Organization › Analytics › Usage ### Get Token Usage By Dimension ## Beta › Organization › Analytics › Cost ### Get Cost By Dimension
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 9
99
1010### Anthropic Beta
1111
12- `AnthropicBeta = string or "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 49 more`
12- `AnthropicBeta = string or "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 51 more`
1313
1414 - `string`
1515
from line 117
117117
118118 - `"webhooks-2026-10-07"`
119119
120 - `"message-threads-2026-08-12"`
121
122 - `"analytics-usage-cost-2026-08-24"`
123
120124### Beta API Error
121125
122126- `BetaAPIError object`
from line 601
597601
598602 - `"webhooks-2026-10-07"`
599603
604 - `"message-threads-2026-08-12"`
605
606 - `"analytics-usage-cost-2026-08-24"`
607
600608- `"anthropic-workspace-id": optional string`
601609
602610 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 943
935943 "deprecated_at": "2019-12-27T18:11:19.117Z",
936944 "display_name": "Claude Opus 5.5",
937945 "lifecycle": "active",
938 "line": "haiku",
946 "line": "opus",
939947 "max_input_tokens": 0,
940948 "max_tokens": 0,
941949 "retires_at": "2019-12-27T18:11:19.117Z",
from line 1088
10801088
10811089 - `"webhooks-2026-10-07"`
10821090
1091 - `"message-threads-2026-08-12"`
1092
1093 - `"analytics-usage-cost-2026-08-24"`
1094
10831095- `"anthropic-workspace-id": optional string`
10841096
10851097 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1416
14041416 "deprecated_at": "2019-12-27T18:11:19.117Z",
14051417 "display_name": "Claude Opus 5.5",
14061418 "lifecycle": "active",
1407 "line": "haiku",
1419 "line": "opus",
14081420 "max_input_tokens": 0,
14091421 "max_tokens": 0,
14101422 "retires_at": "2019-12-27T18:11:19.117Z",
from line 1554
15421554
15431555 - `"webhooks-2026-10-07"`
15441556
1557 - `"message-threads-2026-08-12"`
1558
1559 - `"analytics-usage-cost-2026-08-24"`
1560
15451561- `"anthropic-user-profile-id": optional string`
15461562
15471563 The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization.
from line 5495
54795495
54805496 - `BetaThinkingConfigAdaptive object`
54815497
5498- `thread: optional BetaMessageThreadParam or null`
5499
5500 Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.
5501
5502 - `BetaThreadCreateParams object`
5503
5504 Start holding conversation state under this response's `id`.
5505
5506 - `type: "create"`
5507
5508 - `BetaThreadContinueParams object`
5509
5510 Resume from the response named by `previous_message_id`.
5511
5512 - `type: "continue"`
5513
5514 - `previous_message_id: string`
5515
5516 The `id` of the previous response in this Thread.
5517
54825518- `tool_choice: optional BetaToolChoice`
54835519
54845520 How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
from line 7631
75957631
75967632 `double_click`'s config overrides.
75977633
7598 - `defer_loading: optional boolean or null`
7599
7600 Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
7601
7602 - `enabled: optional boolean or null`
7603
7604 Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
7605
7606 - `hold_key: optional BetaComputerHoldKeyConfig or null`
7607
7608 `hold_key`'s config overrides.
7609
7610 - `defer_loading: optional boolean or null`
7611
7612 Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
7613
7614 - `enabled: optional boolean or null`
7615
7616 Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is with
7634
api/beta/agents Changed · +24 / -0 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 129
129129
130130 - `"webhooks-2026-10-07"`
131131
132 - `"message-threads-2026-08-12"`
133
134 - `"analytics-usage-cost-2026-08-24"`
135
132136- `"anthropic-workspace-id": optional string`
133137
134138 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2151
21472151
21482152 - `"webhooks-2026-10-07"`
21492153
2154 - `"message-threads-2026-08-12"`
2155
2156 - `"analytics-usage-cost-2026-08-24"`
2157
21502158- `"anthropic-workspace-id": optional string`
21512159
21522160 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 3207
31993207
32003208 - `"webhooks-2026-10-07"`
32013209
3210 - `"message-threads-2026-08-12"`
3211
3212 - `"analytics-usage-cost-2026-08-24"`
3213
32023214- `"anthropic-workspace-id": optional string`
32033215
32043216 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 4246
42344246
42354247 - `"webhooks-2026-10-07"`
42364248
4249 - `"message-threads-2026-08-12"`
4250
4251 - `"analytics-usage-cost-2026-08-24"`
4252
42374253- `"anthropic-workspace-id": optional string`
42384254
42394255 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 6243
62276243
62286244 - `"webhooks-2026-10-07"`
62296245
6246 - `"message-threads-2026-08-12"`
6247
6248 - `"analytics-usage-cost-2026-08-24"`
6249
62306250- `"anthropic-workspace-id": optional string`
62316251
62326252 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 8225
82058225
82068226 - `server_tool_results: BetaManagedAgentsWebFetchURLSourceToolFilter or null`
82078227
8208 Which of the web_search and web_fetch tools' results contribute URLs that may be fetched. Null when not set, which allows both.
8209
8210 - `user_input: BetaManagedAgentsWebFetchURLSourceUserInput or null`
8211
8212 Whether URLs in the text of user messages may be fetched. Null when not set, which allows them.
8213
8214 - `BetaManagedAgentsWebFetchURLSourceAll object`
8215
8216 Every URL from this source may be fetched. This
8228 Which of the web_search and web_fetch t
api/beta/deployment_runs Changed · +8 / -0 lines
from line 185
185185
186186 - `"webhooks-2026-10-07"`
187187
188 - `"message-threads-2026-08-12"`
189
190 - `"analytics-usage-cost-2026-08-24"`
191
188192- `"anthropic-workspace-id": optional string`
189193
190194 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 591
587591 - `"telemetry-destinations-2026-08-11"`
588592
589593 - `"webhooks-2026-10-07"`
594
595 - `"message-threads-2026-08-12"`
596
597 - `"analytics-usage-cost-2026-08-24"`
590598
591599- `"anthropic-workspace-id": optional string`
592600
api/beta/deployments Changed · +32 / -0 lines
from line 129
129129
130130 - `"webhooks-2026-10-07"`
131131
132 - `"message-threads-2026-08-12"`
133
134 - `"analytics-usage-cost-2026-08-24"`
135
132136- `"anthropic-workspace-id": optional string`
133137
134138 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1327
13231327
13241328 - `"webhooks-2026-10-07"`
13251329
1330 - `"message-threads-2026-08-12"`
1331
1332 - `"analytics-usage-cost-2026-08-24"`
1333
13261334- `"anthropic-workspace-id": optional string`
13271335
13281336 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2072
20642072
20652073 - `"webhooks-2026-10-07"`
20662074
2075 - `"message-threads-2026-08-12"`
2076
2077 - `"analytics-usage-cost-2026-08-24"`
2078
20672079- `"anthropic-workspace-id": optional string`
20682080
20692081 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2808
27962808
27972809 - `"webhooks-2026-10-07"`
27982810
2811 - `"message-threads-2026-08-12"`
2812
2813 - `"analytics-usage-cost-2026-08-24"`
2814
27992815- `"anthropic-workspace-id": optional string`
28002816
28012817 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 3954
39383954
39393955 - `"webhooks-2026-10-07"`
39403956
3957 - `"message-threads-2026-08-12"`
3958
3959 - `"analytics-usage-cost-2026-08-24"`
3960
39413961- `"anthropic-workspace-id": optional string`
39423962
39433963 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 4691
46714691
46724692 - `"webhooks-2026-10-07"`
46734693
4694 - `"message-threads-2026-08-12"`
4695
4696 - `"analytics-usage-cost-2026-08-24"`
4697
46744698- `"anthropic-workspace-id": optional string`
46754699
46764700 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 5090
50665090
50675091 - `"webhooks-2026-10-07"`
50685092
5093 - `"message-threads-2026-08-12"`
5094
5095 - `"analytics-usage-cost-2026-08-24"`
5096
50695097- `"anthropic-workspace-id": optional string`
50705098
50715099 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 5826
57985826 - `"telemetry-destinations-2026-08-11"`
57995827
58005828 - `"webhooks-2026-10-07"`
5829
5830 - `"message-threads-2026-08-12"`
5831
5832 - `"analytics-usage-cost-2026-08-24"`
58015833
58025834- `"anthropic-workspace-id": optional string`
58035835
api/beta/dreams Changed · +20 / -0 lines
from line 133
133133
134134 - `"webhooks-2026-10-07"`
135135
136 - `"message-threads-2026-08-12"`
137
138 - `"analytics-usage-cost-2026-08-24"`
139
136140- `"anthropic-workspace-id": optional string`
137141
138142 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 726
722726
723727 - `"webhooks-2026-10-07"`
724728
729 - `"message-threads-2026-08-12"`
730
731 - `"analytics-usage-cost-2026-08-24"`
732
725733- `"anthropic-workspace-id": optional string`
726734
727735 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1152
11441152
11451153 - `"webhooks-2026-10-07"`
11461154
1155 - `"message-threads-2026-08-12"`
1156
1157 - `"analytics-usage-cost-2026-08-24"`
1158
11471159- `"anthropic-workspace-id": optional string`
11481160
11491161 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1573
15611573
15621574 - `"webhooks-2026-10-07"`
15631575
1576 - `"message-threads-2026-08-12"`
1577
1578 - `"analytics-usage-cost-2026-08-24"`
1579
15641580- `"anthropic-workspace-id": optional string`
15651581
15661582 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1994
19781994 - `"telemetry-destinations-2026-08-11"`
19791995
19801996 - `"webhooks-2026-10-07"`
1997
1998 - `"message-threads-2026-08-12"`
1999
2000 - `"analytics-usage-cost-2026-08-24"`
19812001
19822002- `"anthropic-workspace-id": optional string`
19832003
api/beta/environments Changed · +56 / -0 lines
from line 129
129129
130130 - `"webhooks-2026-10-07"`
131131
132 - `"message-threads-2026-08-12"`
133
134 - `"analytics-usage-cost-2026-08-24"`
135
132136- `"anthropic-workspace-id": optional string`
133137
134138 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 612
608612
609613 - `"webhooks-2026-10-07"`
610614
615 - `"message-threads-2026-08-12"`
616
617 - `"analytics-usage-cost-2026-08-24"`
618
611619- `"anthropic-workspace-id": optional string`
612620
613621 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 951
943951
944952 - `"webhooks-2026-10-07"`
945953
954 - `"message-threads-2026-08-12"`
955
956 - `"analytics-usage-cost-2026-08-24"`
957
946958- `"anthropic-workspace-id": optional string`
947959
948960 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1281
12691281
12701282 - `"webhooks-2026-10-07"`
12711283
1284 - `"message-threads-2026-08-12"`
1285
1286 - `"analytics-usage-cost-2026-08-24"`
1287
12721288- `"anthropic-workspace-id": optional string`
12731289
12741290 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1733
17171733
17181734 - `"webhooks-2026-10-07"`
17191735
1736 - `"message-threads-2026-08-12"`
1737
1738 - `"analytics-usage-cost-2026-08-24"`
1739
17201740- `"anthropic-workspace-id": optional string`
17211741
17221742 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1906
18861906
18871907 - `"webhooks-2026-10-07"`
18881908
1909 - `"message-threads-2026-08-12"`
1910
1911 - `"analytics-usage-cost-2026-08-24"`
1912
18891913- `"anthropic-workspace-id": optional string`
18901914
18911915 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2706
26822706
26832707 - `"webhooks-2026-10-07"`
26842708
2709 - `"message-threads-2026-08-12"`
2710
2711 - `"analytics-usage-cost-2026-08-24"`
2712
26852713- `"anthropic-workspace-id": optional string`
26862714
26872715 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2976
29482976
29492977 - `"webhooks-2026-10-07"`
29502978
2979 - `"message-threads-2026-08-12"`
2980
2981 - `"analytics-usage-cost-2026-08-24"`
2982
29512983- `"Anthropic-Worker-ID": optional string`
29522984
29532985 Unique identifier for the specific worker polling, used to track aggregated environment-level work metrics in Console
from line 3232
32003232
32013233 - `"webhooks-2026-10-07"`
32023234
3235 - `"message-threads-2026-08-12"`
3236
3237 - `"analytics-usage-cost-2026-08-24"`
3238
32033239#### Returns
32043240
32053241- `BetaSelfHostedWork object`
from line 3495
34593495
34603496 - `"webhooks-2026-10-07"`
34613497
3498 - `"message-threads-2026-08-12"`
3499
3500 - `"analytics-usage-cost-2026-08-24"`
3501
34623502#### Returns
34633503
34643504- `BetaSelfHostedWorkHeartbeatResponse object`
from line 3691
36513691
36523692 - `"webhooks-2026-10-07"`
36533693
3694 - `"message-threads-2026-08-12"`
3695
3696 - `"analytics-usage-cost-2026-08-24"`
3697
36543698- `"anthropic-workspace-id": optional string`
36553699
36563700 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 3969
39253969
39263970 - `"webhooks-2026-10-07"`
39273971
3972 - `"message-threads-2026-08-12"`
3973
3974 - `"analytics-usage-cost-2026-08-24"`
3975
39283976#### Returns
39293977
39303978- `BetaSelfHostedWorkListResponse object`
from line 4230
41824230
41834231 - `"webhooks-2026-10-07"`
41844232
4233 - `"message-threads-2026-08-12"`
4234
4235 - `"analytics-usage-cost-2026-08-24"`
4236
41854237- `"anthropic-workspace-id": optional string`
41864238
41874239 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 4495
44434495 - `"telemetry-destinations-2026-08-11"`
44444496
44454497 - `"webhooks-2026-10-07"`
4498
4499 - `"message-threads-2026-08-12"`
4500
4501 - `"analytics-usage-cost-2026-08-24"`
44464502
44474503- `"anthropic-workspace-id": optional string`
44484504
api/beta/environments/work Changed · +32 / -0 lines
from line 137
137137
138138 - `"webhooks-2026-10-07"`
139139
140 - `"message-threads-2026-08-12"`
141
142 - `"analytics-usage-cost-2026-08-24"`
143
140144- `"anthropic-workspace-id": optional string`
141145
142146 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 407
403407
404408 - `"webhooks-2026-10-07"`
405409
410 - `"message-threads-2026-08-12"`
411
412 - `"analytics-usage-cost-2026-08-24"`
413
406414- `"Anthropic-Worker-ID": optional string`
407415
408416 Unique identifier for the specific worker polling, used to track aggregated environment-level work metrics in Console
from line 663
655663
656664 - `"webhooks-2026-10-07"`
657665
666 - `"message-threads-2026-08-12"`
667
668 - `"analytics-usage-cost-2026-08-24"`
669
658670### Returns
659671
660672- `BetaSelfHostedWork object`
from line 926
914926
915927 - `"webhooks-2026-10-07"`
916928
929 - `"message-threads-2026-08-12"`
930
931 - `"analytics-usage-cost-2026-08-24"`
932
917933### Returns
918934
919935- `BetaSelfHostedWorkHeartbeatResponse object`
from line 1122
11061122
11071123 - `"webhooks-2026-10-07"`
11081124
1125 - `"message-threads-2026-08-12"`
1126
1127 - `"analytics-usage-cost-2026-08-24"`
1128
11091129- `"anthropic-workspace-id": optional string`
11101130
11111131 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1400
13801400
13811401 - `"webhooks-2026-10-07"`
13821402
1403 - `"message-threads-2026-08-12"`
1404
1405 - `"analytics-usage-cost-2026-08-24"`
1406
13831407### Returns
13841408
13851409- `BetaSelfHostedWorkListResponse object`
from line 1661
16371661
16381662 - `"webhooks-2026-10-07"`
16391663
1664 - `"message-threads-2026-08-12"`
1665
1666 - `"analytics-usage-cost-2026-08-24"`
1667
16401668- `"anthropic-workspace-id": optional string`
16411669
16421670 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1926
18981926 - `"telemetry-destinations-2026-08-11"`
18991927
19001928 - `"webhooks-2026-10-07"`
1929
1930 - `"message-threads-2026-08-12"`
1931
1932 - `"analytics-usage-cost-2026-08-24"`
19011933
19021934- `"anthropic-workspace-id": optional string`
19031935
api/beta/files Changed · +20 / -0 lines
from line 129
129129
130130 - `"webhooks-2026-10-07"`
131131
132 - `"message-threads-2026-08-12"`
133
134 - `"analytics-usage-cost-2026-08-24"`
135
132136- `"anthropic-workspace-id": optional string`
133137
134138 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 392
388392
389393 - `"webhooks-2026-10-07"`
390394
395 - `"message-threads-2026-08-12"`
396
397 - `"analytics-usage-cost-2026-08-24"`
398
391399- `"anthropic-workspace-id": optional string`
392400
393401 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 634
626634
627635 - `"webhooks-2026-10-07"`
628636
637 - `"message-threads-2026-08-12"`
638
639 - `"analytics-usage-cost-2026-08-24"`
640
629641- `"anthropic-workspace-id": optional string`
630642
631643 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 782
770782
771783 - `"webhooks-2026-10-07"`
772784
785 - `"message-threads-2026-08-12"`
786
787 - `"analytics-usage-cost-2026-08-24"`
788
773789- `"anthropic-workspace-id": optional string`
774790
775791 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1012
9961012 - `"telemetry-destinations-2026-08-11"`
9971013
9981014 - `"webhooks-2026-10-07"`
1015
1016 - `"message-threads-2026-08-12"`
1017
1018 - `"analytics-usage-cost-2026-08-24"`
9991019
10001020- `"anthropic-workspace-id": optional string`
10011021
api/beta/memory_stores Changed · +56 / -0 lines
from line 129
129129
130130 - `"webhooks-2026-10-07"`
131131
132 - `"message-threads-2026-08-12"`
133
134 - `"analytics-usage-cost-2026-08-24"`
135
132136- `"anthropic-workspace-id": optional string`
133137
134138 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 395
391395
392396 - `"webhooks-2026-10-07"`
393397
398 - `"message-threads-2026-08-12"`
399
400 - `"analytics-usage-cost-2026-08-24"`
401
394402- `"anthropic-workspace-id": optional string`
395403
396404 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 618
610618
611619 - `"webhooks-2026-10-07"`
612620
621 - `"message-threads-2026-08-12"`
622
623 - `"analytics-usage-cost-2026-08-24"`
624
613625- `"anthropic-workspace-id": optional string`
614626
615627 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 836
824836
825837 - `"webhooks-2026-10-07"`
826838
839 - `"message-threads-2026-08-12"`
840
841 - `"analytics-usage-cost-2026-08-24"`
842
827843- `"anthropic-workspace-id": optional string`
828844
829845 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1078
10621078
10631079 - `"webhooks-2026-10-07"`
10641080
1081 - `"message-threads-2026-08-12"`
1082
1083 - `"analytics-usage-cost-2026-08-24"`
1084
10651085- `"anthropic-workspace-id": optional string`
10661086
10671087 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1251
12311251
12321252 - `"webhooks-2026-10-07"`
12331253
1254 - `"message-threads-2026-08-12"`
1255
1256 - `"analytics-usage-cost-2026-08-24"`
1257
12341258- `"anthropic-workspace-id": optional string`
12351259
12361260 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1550
15261550
15271551 - `"webhooks-2026-10-07"`
15281552
1553 - `"message-threads-2026-08-12"`
1554
1555 - `"analytics-usage-cost-2026-08-24"`
1556
15291557- `"anthropic-workspace-id": optional string`
15301558
15311559 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1843
18151843
18161844 - `"webhooks-2026-10-07"`
18171845
1846 - `"message-threads-2026-08-12"`
1847
1848 - `"analytics-usage-cost-2026-08-24"`
1849
18181850- `"anthropic-workspace-id": optional string`
18191851
18201852 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2118
20862118
20872119 - `"webhooks-2026-10-07"`
20882120
2121 - `"message-threads-2026-08-12"`
2122
2123 - `"analytics-usage-cost-2026-08-24"`
2124
20892125- `"anthropic-workspace-id": optional string`
20902126
20912127 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2368
23322368
23332369 - `"webhooks-2026-10-07"`
23342370
2371 - `"message-threads-2026-08-12"`
2372
2373 - `"analytics-usage-cost-2026-08-24"`
2374
23352375- `"anthropic-workspace-id": optional string`
23362376
23372377 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2638
25982638
25992639 - `"webhooks-2026-10-07"`
26002640
2641 - `"message-threads-2026-08-12"`
2642
2643 - `"analytics-usage-cost-2026-08-24"`
2644
26012645- `"anthropic-workspace-id": optional string`
26022646
26032647 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 2889
28452889
28462890 - `"webhooks-2026-10-07"`
28472891
2892 - `"message-threads-2026-08-12"`
2893
2894 - `"analytics-usage-cost-2026-08-24"`
2895
28482896- `"anthropic-workspace-id": optional string`
28492897
28502898 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 3225
31773225
31783226 - `"webhooks-2026-10-07"`
31793227
3228 - `"message-threads-2026-08-12"`
3229
3230 - `"analytics-usage-cost-2026-08-24"`
3231
31803232- `"anthropic-workspace-id": optional string`
31813233
31823234 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 3541
34893541 - `"telemetry-destinations-2026-08-11"`
34903542
34913543 - `"webhooks-2026-10-07"`
3544
3545 - `"message-threads-2026-08-12"`
3546
3547 - `"analytics-usage-cost-2026-08-24"`
34923548
34933549- `"anthropic-workspace-id": optional string`
34943550
api/beta/memory_stores/memories Changed · +20 / -0 lines
from line 151
151151
152152 - `"webhooks-2026-10-07"`
153153
154 - `"message-threads-2026-08-12"`
155
156 - `"analytics-usage-cost-2026-08-24"`
157
154158- `"anthropic-workspace-id": optional string`
155159
156160 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 444
440444
441445 - `"webhooks-2026-10-07"`
442446
447 - `"message-threads-2026-08-12"`
448
449 - `"analytics-usage-cost-2026-08-24"`
450
443451- `"anthropic-workspace-id": optional string`
444452
445453 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 719
711719
712720 - `"webhooks-2026-10-07"`
713721
722 - `"message-threads-2026-08-12"`
723
724 - `"analytics-usage-cost-2026-08-24"`
725
714726- `"anthropic-workspace-id": optional string`
715727
716728 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 969
957969
958970 - `"webhooks-2026-10-07"`
959971
972 - `"message-threads-2026-08-12"`
973
974 - `"analytics-usage-cost-2026-08-24"`
975
960976- `"anthropic-workspace-id": optional string`
961977
962978 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 1238
12221238 - `"telemetry-destinations-2026-08-11"`
12231239
12241240 - `"webhooks-2026-10-07"`
1241
1242 - `"message-threads-2026-08-12"`
1243
1244 - `"analytics-usage-cost-2026-08-24"`
12251245
12261246- `"anthropic-workspace-id": optional string`
12271247
api/beta/memory_stores/memory_versions Changed · +12 / -0 lines
from line 209
209209
210210 - `"webhooks-2026-10-07"`
211211
212 - `"message-threads-2026-08-12"`
213
214 - `"analytics-usage-cost-2026-08-24"`
215
212216- `"anthropic-workspace-id": optional string`
213217
214218 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 545
541545
542546 - `"webhooks-2026-10-07"`
543547
548 - `"message-threads-2026-08-12"`
549
550 - `"analytics-usage-cost-2026-08-24"`
551
544552- `"anthropic-workspace-id": optional string`
545553
546554 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 861
853861 - `"telemetry-destinations-2026-08-11"`
854862
855863 - `"webhooks-2026-10-07"`
864
865 - `"message-threads-2026-08-12"`
866
867 - `"analytics-usage-cost-2026-08-24"`
856868
857869- `"anthropic-workspace-id": optional string`
858870
api/beta/messages Changed · +114 / -0 lines
### Beta Message Thread Param ### Beta Thread Continue Params ### Beta Thread Create Params
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 133
133133
134134 - `"webhooks-2026-10-07"`
135135
136 - `"message-threads-2026-08-12"`
137
138 - `"analytics-usage-cost-2026-08-24"`
139
136140- `"anthropic-user-profile-id": optional string`
137141
138142 The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization.
from line 4074
40704074
40714075 - `BetaThinkingConfigAdaptive object`
40724076
4077- `thread: optional BetaMessageThreadParam or null`
4078
4079 Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.
4080
4081 - `BetaThreadCreateParams object`
4082
4083 Start holding conversation state under this response's `id`.
4084
4085 - `type: "create"`
4086
4087 - `BetaThreadContinueParams object`
4088
4089 Resume from the response named by `previous_message_id`.
4090
4091 - `type: "continue"`
4092
4093 - `previous_message_id: string`
4094
4095 The `id` of the previous response in this Thread.
4096
40734097- `tool_choice: optional BetaToolChoice`
40744098
40754099 How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
from line 7046
70227046
70237047 Powerful intelligence for coding, knowledge work, and long-running agents
70247048
7025 - `"claude-mythos-5-1"`
7026
7027 Our most capable model for cybersecurity and biology research, available through trusted access programs
7028
7029 - `"claude-sonnet-5"`
7030
7031 Efficient model for coding and agents
7032
7033 - `"claude-fable-5"`
7034
7035 Next generation of intelligence for the hardest knowledge work and coding problems
7036
7037 - `"claude-mythos-5"`
7038
7039 Most capable model for cybersecurity and biology research
7040
7041 - `"claude-opus-5"`
7042
7043 Powerful intelligence for long-running agents and coding
7044
7045 - `"claude-opus-4-8"`
7046
7047 Powerful intelligence for long-running agents and coding
7048
7049
7049
api/beta/messages/batches Changed · +44 / -0 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 133
133133
134134 - `"webhooks-2026-10-07"`
135135
136 - `"message-threads-2026-08-12"`
137
138 - `"analytics-usage-cost-2026-08-24"`
139
136140- `"anthropic-user-profile-id": optional string`
137141
138142 The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored.
from line 4094
40904094
40914095 - `BetaThinkingConfigAdaptive object`
40924096
4097 - `thread: optional BetaMessageThreadParam or null`
4098
4099 Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.
4100
4101 - `BetaThreadCreateParams object`
4102
4103 Start holding conversation state under this response's `id`.
4104
4105 - `type: "create"`
4106
4107 - `BetaThreadContinueParams object`
4108
4109 Resume from the response named by `previous_message_id`.
4110
4111 - `type: "continue"`
4112
4113 - `previous_message_id: string`
4114
4115 The `id` of the previous response in this Thread.
4116
40934117 - `tool_choice: optional BetaToolChoice`
40944118
40954119 How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
from line 4609
45854609
45864610 - `"webhooks-2026-10-07"`
45874611
4612 - `"message-threads-2026-08-12"`
4613
4614 - `"analytics-usage-cost-2026-08-24"`
4615
45884616- `"anthropic-workspace-id": optional string`
45894617
45904618 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 4905
48774905
48784906 - `"webhooks-2026-10-07"`
48794907
4908 - `"message-threads-2026-08-12"`
4909
4910 - `"analytics-usage-cost-2026-08-24"`
4911
48804912- `"anthropic-workspace-id": optional string`
48814913
48824914 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 5210
51785210
51795211 - `"webhooks-2026-10-07"`
51805212
5213 - `"message-threads-2026-08-12"`
5214
5215 - `"analytics-usage-cost-2026-08-24"`
5216
51815217- `"anthropic-workspace-id": optional string`
51825218
51835219 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 5497
54615497
54625498 - `"webhooks-2026-10-07"`
54635499
5500 - `"message-threads-2026-08-12"`
5501
5502 - `"analytics-usage-cost-2026-08-24"`
5503
54645504- `"anthropic-workspace-id": optional string`
54655505
54665506 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 5676
56365676
56375677 - `"webhooks-2026-10-07"`
56385678
5679 - `"message-threads-2026-08-12"`
5680
5681 - `"analytics-usage-cost-2026-08-24"`
5682
56395683- `"anthropic-workspace-id": optional string`
56405684
56415685 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 7246
72027246
72037247 - `enabled: optional boolean or null`
72047248
7205 Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
7206
7207 - `right_click: optional BetaBrowserRightClickConfig or null`
7208
7209 `right_click`'s config overrides.
7210
7211 - `defer_loading: optional boolean or null`
7212
7213 Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
7214
7215 - `enabled: optional boolean or null`
7216
7217 Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
7218
7219 - `screenshot: optional BetaBrowserScreenshotConfig or null`
7220
7221 `screenshot`'s config overrides.
7222
7223 - `defer_loading: optional boolean or null`
7224
7225 Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
7226
7227 - `enabled: optional boolean or null
7249 Whether this member i
api/beta/messages/batches/create Changed · +24 / -0 lines
from line 131
131131
132132 - `"webhooks-2026-10-07"`
133133
134 - `"message-threads-2026-08-12"`
135
136 - `"analytics-usage-cost-2026-08-24"`
137
134138- `"anthropic-user-profile-id": optional string`
135139
136140 The user profile ID to attribute the requests in this batch to. Use when acting on behalf of a party other than your organization. Applies to every request in the batch; an individual request whose `user_profile_id` body field conflicts with this header is errored.
from line 4091
40874091 - `BetaThinkingConfigBetweenTools object`
40884092
40894093 - `BetaThinkingConfigAdaptive object`
4094
4095 - `thread: optional BetaMessageThreadParam or null`
4096
4097 Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.
4098
4099 - `BetaThreadCreateParams object`
4100
4101 Start holding conversation state under this response's `id`.
4102
4103 - `type: "create"`
4104
4105 - `BetaThreadContinueParams object`
4106
4107 Resume from the response named by `previous_message_id`.
4108
4109 - `type: "continue"`
4110
4111 - `previous_message_id: string`
4112
4113 The `id` of the previous response in this Thread.
40904114
40914115 - `tool_choice: optional BetaToolChoice`
40924116
api/beta/messages/create Changed · +24 / -0 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 131
131131
132132 - `"webhooks-2026-10-07"`
133133
134 - `"message-threads-2026-08-12"`
135
136 - `"analytics-usage-cost-2026-08-24"`
137
134138- `"anthropic-user-profile-id": optional string`
135139
136140 The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization.
from line 4072
40684072
40694073 - `BetaThinkingConfigAdaptive object`
40704074
4075- `thread: optional BetaMessageThreadParam or null`
4076
4077 Server-held conversation state (a Thread). `{"type": "create"}` asks the server to hold this conversation's state under the response's `id`; `{"type": "continue", "previous_message_id": ...}` resumes from a previous response so only the new turn's messages are sent. The response shape is unchanged.
4078
4079 - `BetaThreadCreateParams object`
4080
4081 Start holding conversation state under this response's `id`.
4082
4083 - `type: "create"`
4084
4085 - `BetaThreadContinueParams object`
4086
4087 Resume from the response named by `previous_message_id`.
4088
4089 - `type: "continue"`
4090
4091 - `previous_message_id: string`
4092
4093 The `id` of the previous response in this Thread.
4094
40714095- `tool_choice: optional BetaToolChoice`
40724096
40734097 How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
from line 7044
70207044
70217045 Powerful intelligence for coding, knowledge work, and long-running agents
70227046
7023 - `"claude-mythos-5-1"`
7024
7025 Our most capable model for cybersecurity and biology research, available through trusted access programs
7026
7027 - `"claude-sonnet-5"`
7028
7029 Efficient model for coding and agents
7030
7031 - `"claude-fable-5"`
7032
7033 Next generation of intelligence for the hardest knowledge work and coding problems
7034
7035 - `"claude-mythos-5"`
7036
7037 Most capable model for cybersecurity and biology research
7038
7039 - `"claude-opus-5"`
7040
7041 Powerful intelligence for long-running agents and coding
7042
7043 - `"claude-opus-4-8"`
7044
7045 Powerful intelligence for long-running agents and coding
7046
7047
7047
api/beta/models Changed · +10 / -2 lines
from line 161
161161
162162 - `"webhooks-2026-10-07"`
163163
164 - `"message-threads-2026-08-12"`
165
166 - `"analytics-usage-cost-2026-08-24"`
167
164168- `"anthropic-workspace-id": optional string`
165169
166170 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 503
499503 "deprecated_at": "2019-12-27T18:11:19.117Z",
500504 "display_name": "Claude Opus 5.5",
501505 "lifecycle": "active",
502 "line": "haiku",
506 "line": "opus",
503507 "max_input_tokens": 0,
504508 "max_tokens": 0,
505509 "retires_at": "2019-12-27T18:11:19.117Z",
from line 648
644648
645649 - `"webhooks-2026-10-07"`
646650
651 - `"message-threads-2026-08-12"`
652
653 - `"analytics-usage-cost-2026-08-24"`
654
647655- `"anthropic-workspace-id": optional string`
648656
649657 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 976
968976 "deprecated_at": "2019-12-27T18:11:19.117Z",
969977 "display_name": "Claude Opus 5.5",
970978 "lifecycle": "active",
971 "line": "haiku",
979 "line": "opus",
972980 "max_input_tokens": 0,
973981 "max_tokens": 0,
974982 "retires_at": "2019-12-27T18:11:19.117Z",
api/beta/models/list Changed · +5 / -1 lines
from line 159
159159
160160 - `"webhooks-2026-10-07"`
161161
162 - `"message-threads-2026-08-12"`
163
164 - `"analytics-usage-cost-2026-08-24"`
165
162166- `"anthropic-workspace-id": optional string`
163167
164168 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 501
497501 "deprecated_at": "2019-12-27T18:11:19.117Z",
498502 "display_name": "Claude Opus 5.5",
499503 "lifecycle": "active",
500 "line": "haiku",
504 "line": "opus",
501505 "max_input_tokens": 0,
502506 "max_tokens": 0,
503507 "retires_at": "2019-12-27T18:11:19.117Z",
api/beta/models/retrieve Changed · +5 / -1 lines
from line 135
135135
136136 - `"webhooks-2026-10-07"`
137137
138 - `"message-threads-2026-08-12"`
139
140 - `"analytics-usage-cost-2026-08-24"`
141
138142- `"anthropic-workspace-id": optional string`
139143
140144 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
from line 463
459463 "deprecated_at": "2019-12-27T18:11:19.117Z",
460464 "display_name": "Claude Opus 5.5",
461465 "lifecycle": "active",
462 "line": "haiku",
466 "line": "opus",
463467 "max_input_tokens": 0,
464468 "max_tokens": 0,
465469 "retires_at": "2019-12-27T18:11:19.117Z",
api/beta/organization Changed · +1870 / -30 lines
## Organization › Analytics › Usage ### Get Token Usage By Dimension ## Organization › Analytics › Cost ### Get Cost By Dimension
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 1713
17131713
17141714 - `"webhooks-2026-10-07"`
17151715
1716 - `"message-threads-2026-08-12"`
1717
1718 - `"analytics-usage-cost-2026-08-24"`
1719
17161720#### Body parameters
17171721
17181722- `issuer_url: string`
from line 2119
21152119
21162120 - `"webhooks-2026-10-07"`
21172121
2122 - `"message-threads-2026-08-12"`
2123
2124 - `"analytics-usage-cost-2026-08-24"`
2125
21182126#### Returns
21192127
21202128- `data: array of BetaFederationIssuer`
from line 2436
24282436
24292437 - `"webhooks-2026-10-07"`
24302438
2439 - `"message-threads-2026-08-12"`
2440
2441 - `"analytics-usage-cost-2026-08-24"`
2442
24312443#### Returns
24322444
24332445- `BetaFederationIssuer object`
from line 2756
27442756
27452757 - `"webhooks-2026-10-07"`
27462758
2759 - `"message-threads-2026-08-12"`
2760
2761 - `"analytics-usage-cost-2026-08-24"`
2762
27472763#### Body parameters
27482764
27492765- `check_jti: optional boolean or null`
from line 3154
31383154
31393155 - `"webhooks-2026-10-07"`
31403156
3157 - `"message-threads-2026-08-12"`
3158
3159 - `"analytics-usage-cost-2026-08-24"`
3160
31413161#### Returns
31423162
31433163- `BetaFederationIssuer object`
from line 3478
34583478
34593479 - `"webhooks-2026-10-07"`
34603480
3481 - `"message-threads-2026-08-12"`
3482
3483 - `"analytics-usage-cost-2026-08-24"`
3484
34613485#### Body parameters
34623486
34633487- `issuer_id: string`
from line 3909
38853909
38863910 - `"webhooks-2026-10-07"`
38873911
3912 - `"message-threads-2026-08-12"`
3913
3914 - `"analytics-usage-cost-2026-08-24"`
3915
38883916#### Returns
38893917
38903918- `data: array of BetaFederationRule`
from line 4226
41984226
41994227 - `"webhooks-2026-10-07"`
42004228
4229 - `"message-threads-2026-08-12"`
4230
4231 - `"analytics-usage-cost-2026-08-24"`
4232
42014233#### Returns
42024234
42034235- `BetaFederationRule object`
from line 4561
45294561
45304562 - `"webhooks-2026-10-07"`
45314563
4564 - `"message-threads-2026-08-12"`
4565
4566 - `"analytics-usage-cost-2026-08-24"`
4567
45324568#### Body parameters
45334569
45344570- `applies_to_all_workspaces: optional boolean or null`
from line 4968
49324968
49334969 - `"webhooks-2026-10-07"`
49344970
4971 - `"message-threads-2026-08-12"`
4972
4973 - `"analytics-usage-cost-2026-08-24"`
4974
49354975#### Returns
49364976
49374977- `BetaFederationRule object`
from line 5299
52595299
52605300 - `"webhooks-2026-10-07"`
52615301
5302 - `"message-threads-2026-08-12"`
5303
5304 - `"analytics-usage-cost-2026-08-24"`
5305
52625306#### Body parameters
52635307
52645308- `workspace_id: string`
from line 5514
54705514
54715515 - `"webhooks-2026-10-07"`
54725516
5517 - `"message-threads-2026-08-12"`
5518
5519 - `"analytics-usage-cost-2026-08-24"`
5520
54735521#### Returns
54745522
54755523- `data: array of BetaFederationRuleWorkspace`
from line 5719
56715719
56725720 - `"webhooks-2026-10-07"`
56735721
5722 - `"message-threads-2026-08-12"`
5723
5724 - `"analytics-usage-cost-2026-08-24"`
5725
56745726#### Returns
56755727
56765728- `type: "federation_rule_workspace_deleted"`
from line 6396
63446396
63456397 - `"webhooks-2026-10-07"`
63466398
6399 - `"message-threads-2026-08-12"`
6400
6401 - `"analytics-usage-cost-2026-08-24"`
6402
63476403#### Body parameters
63486404
63496405- `name: string`
from line 6663
66076663
66086664 - `"webhooks-2026-10-07"`
66096665
6666 - `"message-threads-2026-08-12"`
6667
6668 - `"analytics-usage-cost-2026-08-24"`
6669
66106670#### Returns
66116671
66126672- `data: array of BetaServiceAccount`
from line 6892
68326892
68336893 - `"webhooks-2026-10-07"`
68346894
6895 - `"message-threads-2026-08-12"`
6896
6897 - `"analytics-usage-cost-2026-08-24"`
6898
68356899#### Returns
68366900
68376901- `BetaServiceAccount object`
from line 7122
70587122
70597123 - `"webhooks-2026-10-07"`
70607124
7125 - `"message-threads-2026-08-12"`
7126
7127 - `"analytics-usage-cost-2026-08-24"`
7128
70617129#### Body parameters
70627130
70637131- `description: optional string or null`
from line 7370
73027370
73037371 - `"webhooks-2026-10-07"`
73047372
7373 - `"message-threads-2026-08-12"`
7374
7375 - `"analytics-usage-cost-2026-08-24"`
7376
73057377#### Returns
73067378
73077379- `BetaServiceAccount object`
from line 7605
75337605
75347606 - `"webhooks-2026-10-07"`
75357607
7608 - `"message-threads-2026-08-12"`
7609
7610 - `"analytics-usage-cost-2026-08-24"`
7611
75367612#### Body parameters
75377613
75387614- `workspace_id: string`
from line 7849
77737849
77747850 - `"webhooks-2026-10-07"`
77757851
7852 - `"message-threads-2026-08-12"`
7853
7854 - `"analytics-usage-cost-2026-08-24"`
7855
77767856#### Returns
77777857
77787858- `data: array of BetaServiceAccountWorkspaceMember`
from line 8065
79858065
79868066 - `"webhooks-2026-10-07"`
79878067
8068 - `"message-threads-2026-08-12"`
8069
8070 - `"analytics-usage-cost-2026-08-24"`
8071
79888072#### Returns
79898073
79908074- `type: "service_account_workspace_member_deleted"`
from line 8817
87338817
87348818 - `"webhooks-2026-10-07"`
87358819
8820 - `"message-threads-2026-08-12"`
8821
8822 - `"analytics-usage-cost-2026-08-24"`
8823
87368824#### Body parameters
87378825
87388826- `name: string`
from line 10480
1039210480
1039310481**GET** `/v1/organizations/workspaces/{workspace_id}/service_accounts`
1039410482
10395**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api?sdk_languages=http).
10396
10397List the service accounts that are members of a workspace.
10398
10399Each entry includes the service account's `workspace_role`. Use `limit`
10400and the `next_page` cursor to paginate. Archived workspaces return 400;
10401use `GET /service_accounts/{id}/workspaces` to audit memberships of an
10402archived workspace. The implicit default-workspace membership is not
10403included in this list. Memberships of archived service accounts are
10404omitted from the results.
10405
10406#### Path parameters
10407
10408- `workspace_id: string`
10409
10410 ID of the workspace.
10411
10412#### Query parameters
10413
10414- `limit: optional number`
10415
10416 Number of results per page.
10417
10418 default: 20, minimum: 1, maximum: 100
10419
10420- `page: optional string`
10421
10422 Opaque cursor from a previous response's `next_page`.
10423
10424#### Headers
10425
10426- `"anthropic-version": optional string`
10427
10428 The version of the Claude API you want to use.
10429
10430 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning?sdk_languages=http).
10431
10432- `"anthropic-beta": optional array of AnthropicBeta`
10433
10434 Optional header to specify the beta version(s) you want to use.
10435
10436 - `string`
10437
10438 - `"message-batches-2024-09-24"`
10439
10440 - `"prompt-caching-2024-07-31"`
10441
10442 - `"computer-use-2024-10-22"`
10443
10444 - `"computer-use-2025-01-24"`
10445
10446 - `"pdfs-2024-09-25"`
10447
10448 - `"token-counting-2024-11-01"`
10449
10450 - `"token-efficient-tools-2025-02-19"`
10451
10452 - `"output-128k-2025-02-19"`
10453
10454 - `"files-api-2025-04-14"`
10455
10456 - `"mcp-client-2025-04-04"`
10457
10458 - `"mcp-client-2025-11-20"`
10459
10460 - `"dev-full-thinking-2025-05-14"`
10461
10462 - `"interleaved-thinking-2025-05-14"`
10463
10464 - `"code-execution-2025-05-22"`
10465
10466 - `"extended-cache-ttl-2025-04-11"`
10467
10468 - `"context-
10483**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platfor
api/beta/organization/analytics Changed · +1948 / -30 lines
### Beta Analytics Actor ### Beta Analytics Actor Type ### Beta Analytics API Actor ### Beta Analytics Federated Actor ### Beta Analytics Federated Actor AWS Provider ### Beta Analytics Federated Actor Azure Provider ### Beta Analytics Federated Actor GCP Provider ### Beta Analytics Federated Actor OIDC Provider ### Beta Analytics Federated Actor Provider ### Beta Analytics Grouped Cost Type ### Beta Analytics Report User Actor ### Beta Analytics Service Account Actor ### Beta Analytics Service Tier ### Beta Analytics Speed ### Beta Analytics Time Bucket Width ### Beta Analytics Usage Cost Inference Geo ### Beta Analytics Usage Cost Product Filter ### Beta Analytics Usage Cost Sort Order ## Analytics › Usage ### Get Token Usage By Dimension ## Analytics › Cost ### Get Cost By Dimension
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 6
66# Analytics
77
88## Domain types
9
10### Beta Analytics Actor
11
12- `BetaAnalyticsActor = BetaAnalyticsReportUserActor or BetaAnalyticsServiceAccountActor or BetaAnalyticsFederatedActor or BetaAnalyticsAPIActor`
13
14 - `BetaAnalyticsReportUserActor object`
15
16 - `type: "user_actor"`
17
18 Actor type. Always `"user_actor"`.
19
20 - `deleted: boolean`
21
22 True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation.
23
24 - `email_address: string or null`
25
26 The user's current email address, including for users who are no longer members of the organization. Null when the account has been deleted and for system-minted service accounts.
27
28 - `name: string or null`
29
30 The user's current full name. Null when the user has not set one. `"Deleted User"` when the account has been deleted, or when the user is no longer a member and the organization hides removed users' names.
31
32 - `user_id: string`
33
34 Tagged user ID.
35
36 - `BetaAnalyticsServiceAccountActor object`
37
38 - `type: "service_account_actor"`
39
40 - `service_account_id: string`
41
42 Tagged service account ID.
43
44 - `BetaAnalyticsFederatedActor object`
45
46 - `type: "federated_actor"`
47
48 - `provider: BetaAnalyticsFederatedActorProvider`
49
50 The trusted provider that asserted the caller's identity.
51
52 - `BetaAnalyticsFederatedActorAWSProvider object`
53
54 - `type: "aws"`
55
56 - `account_id: string`
57
58 The AWS account the organization is bound to.
59
60 - `signed_principal: string`
61
62 The AWS-signed ARN of the IAM principal that made the requests.
63
64 - `BetaAnalyticsFederatedActorAzureProvider object`
65
66 - `type: "azure"`
67
68 - `subscription_id: string`
69
70 The Azure subscription the organization is bound to.
71
72 - `BetaAnalyticsFederatedActorGCPProvider object`
73
74 - `type: "gcp"`
75
76 - `project_number: string`
77
78 The Google Cloud project the organization is bound to.
79
80 - `BetaAnalyticsFederatedActorOIDCProvider object`
81
82 - `type: "oidc"`
83
84 - `issuer: string or null`
85
86 The federation issuer's URL.
87
88 - `subject: string or null`
89
90 The provider's identifier for the caller: on `aws`, the IAM principal ARN (one role is one actor across its sessions); on `gcp`, the caller's IAM principal identifier as Google Cloud reports it, such as `serviceAccount:<email>`, `user:<email>`, or a `principal://...` URI.
91
92 - `BetaAnalyticsAPIActor object`
93
94 - `type: "api_actor"`
95
96 - `api_key_id: string`
97
98 Tagged API key ID.
99
100### Beta Analytics Actor Type
101
102- `BetaAnalyticsActorType = "api_actor" or "federated_actor" or "service_account_actor" or "user_actor"`
103
104 Kind of identity a row's usage is attributed to.
105
106 - `"api_actor"`
107
108 - `"federated_actor"`
109
110 - `"service_account_actor"`
111
112 - `"user_actor"`
113
114### Beta Analytics API Actor
115
116- `BetaAnalyticsAPIActor object`
117
118 - `type: "api_actor"`
119
120 - `api_key_id: string`
121
122 Tagged API key ID.
9123
10124### Beta Analytics Artifact Activity
11125
from line 1160
10461160
10471161 Number of messages sent in Claude Design sessions
10481162
1163### Beta Analytics Federated Actor
1164
1165- `BetaAnalyticsFederatedActor object`
1166
1167 - `type: "federated_actor"`
1168
1169 - `provider: BetaAnalyticsFederatedActorProvider`
1170
1171 The trusted provider that asserted the caller's identity.
1172
1173 - `BetaAnalyticsFederatedActorAWSProvider object`
1174
1175 - `type: "aws"`
1176
1177 - `account_id: string`
1178
1179 The AWS account the organization is bound to.
1180
1181 - `signed_principal: string`
1182
1183 The AWS-signed ARN of the IAM principal that made the requests.
1184
1185 - `BetaAnalyticsFederatedActorAzureProvider object`
1186
1187 - `type: "azure"`
1188
1189 - `subscription_id: string`
1190
1191 The Azure subscription the organization is bound to.
1192
1193 - `BetaAnalyticsFederatedActorGCPProvider object`
1194
1195 - `type: "gcp"`
1196
1197 - `project_number: string`
1198
1199 The Google Cloud project the organization is bound to.
1200
1201 - `BetaAnalyticsFederatedActorOIDCProvider object`
1202
1203 - `type: "oidc"`
1204
1205 - `issuer: string or null`
1206
1207 The federation issuer's URL.
1208
1209 - `subject: string or null`
1210
1211 The provider's identifier for the caller: on `aws`, the IAM principal ARN (one role is one actor across its sessions); on `gcp`, the caller's IAM principal identifier as Google Cloud reports it, such as `serviceAccount:<email>`, `user:<email>`, or a `principal://...` URI.
1212
1213### Beta Analytics Federated Actor AWS Provider
1214
1215- `BetaAnalyticsFederatedActorAWSProvider object`
1216
1217 - `type: "aws"`
1218
1219 - `account_id: string`
1220
1221 The AWS account the organization is bound to.
1222
1223 - `signed_principal: string`
1224
1225 The AWS-signed ARN of the IAM principal that made the requests.
1226
1227### Beta Analytics Federated Actor Azure Provider
1228
1229- `BetaAnalyticsFederatedActorAzureProvider object`
1230
1231 - `type: "azure"`
1232
1233 - `subscription_id: string`
1234
1235 The Azure subscription the organization is bound to.
1236
1237### Beta Analytics Federated Actor GCP Provider
1238
1239- `BetaAnalyticsFederatedActorGCPProvider object`
1240
1241 - `type: "gcp"`
1242
1243 - `project_number: string`
1244
1245 The Google Cloud project the organization is bound to.
1246
1247### Beta Analytics Federated Actor OIDC Provider
1248
1249- `BetaAnalyticsFederatedActorOIDCProvider object`
1250
1251 - `type: "oidc"`
1252
1253 - `issuer: string or null`
1254
1255 The federation issuer's URL.
1256
1257### Beta Analytics Federated Actor Provider
1258
1259- `BetaAnalyticsFederatedActorProvider = BetaAnalyticsFederatedActorAWSProvider or BetaAnalyticsFederatedActorAzureProvider or BetaAnalyticsFederatedActorGCPProvider or BetaAnalyticsFederatedActorOIDCProvider`
1260
1261 - `BetaAnalyticsFederatedActorAWSProvider object`
1262
1263 - `type: "aws"`
1264
1265 - `account_id: string`
1266
1267 The AWS account the organization is bound to.
1268
1269 - `signed_principal: string`
1270
1271 The AWS-signed ARN of the IAM principal that made the requests.
1272
1273 - `BetaAnalyticsFederatedActorAzureProvider object`
1274
1275 - `type: "azure"`
1276
1277 - `subscription_id: string`
1278
1279 The Azure subscription the organization is bound to.
1280
1281 - `BetaAnalyticsFederatedActorGCPProvider object`
1282
1283 - `type: "gcp"`
1284
1285 - `project_number: string`
1286
1287 The Google Cloud project the organization is bound to.
1288
1289 - `BetaAnalyticsFederatedActorOIDCProvider object`
1290
1291 - `type: "oidc"`
1292
1293 - `issuer: string or null`
1294
1295 The federation issuer's URL.
1296
1297### Beta Analytics Grouped Cost Type
1298
1299- `BetaAnalyticsGroupedCostType = "code_execution" or "session_usage" or "tokens" or "web_search"`
1300
1301 - `"code_execution"`
1302
1303 - `"session_usage"`
1304
1305 - `"tokens"`
1306
1307 - `"web_search"`
1308
10491309### Beta Analytics Inference Geo Filter
10501310
10511311- `BetaAnalyticsInferenceGeoFilter = "global" or "not_available" or "us"`
from line 1586
13261586
13271587 Tagged user identifier (e.g. `user_...`). Present only when the request grouped by `user_id`.
13281588
1589### Beta Analytics Report User Actor
1590
1591- `BetaAnalyticsReportUserActor object`
1592
1593 - `type: "user_actor"`
1594
1595 Actor type. Always `"user_actor"`.
1596
1597 - `deleted: boolean`
1598
1599 True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation.
1600
1601 - `email_address: string or null`
1602
1603 The user's current email address, including for users who are no longer members of the organization. Null when the account has been deleted and for system-minted service accounts.
1604
1605 - `name: string or null`
1606
1607 The user's current full name. Null when the user has not set one. `"Deleted User"` when the account has been deleted, or when the user is no longer a member and the organization hides removed users' names.
1608
1609 - `user_id: string`
1610
1611 Tagged user ID.
1612
13291613### Beta Analytics Science Metrics
13301614
13311615- `BetaAnalyticsScienceMetrics object`
from line 1643
13591643 - `web_search_requests: number`
13601644
13611645 The number of web search requests made.
1646
1647### Beta Analytics Service Account Actor
1648
1649- `BetaAnalyticsServiceAccountActor object`
1650
1651 - `type: "service_account_actor"`
1652
1653 - `service_account_id: string`
1654
1655 Tagged service account ID.
1656
1657### Beta Analytics Service Tier
1658
1659- `BetaAnalyticsServiceTier = "batch" or "flex" or "flex_discount" or 3 more`
1660
1661 - `"batch"`
1662
1663 - `"flex"`
1664
1665 - `"flex_discount"`
1666
1667 - `"priority"`
1668
1669 - `"priority_on_demand"`
1670
1671 - `"standard"`
13621672
13631673### Beta Analytics Single Day Activity Summary
13641674
from line 2030
17202030
17212031 Number of distinct Office Agent sessions in which the skill was used. A skill counts as used only when it is explicitly activated — the model (or the user, via the skill's slash command) invokes it, reading its instructions into context as part of that activation. Skills that are merely installed or listed as available, or whose content reaches the context without an activation (preloaded, hook-injected, or read as a plain file), are not counted. Approximate (HLL, typical error <2%) in date-range mode. Null on aggregated rows where a distinct count cannot be computed.
17222032
2033### Beta Analytics Speed
2034
2035- `BetaAnalyticsSpeed = "fast" or "standard"`
2036
2037 - `"fast"`
2038
2039 - `"standard"`
2040
2041### Beta Analytics Time Bucket Width
2042
2043- `BetaAnalyticsTimeBucketWidth = "1d" or "1h" or "1m"`
2044
2045 - `"1d"`
2046
2047 - `"1h"`
2048
2049 - `"1m"`
2050
17232051### Beta Analytics Token Type
17242052
17252053- `BetaAnalyticsTokenType = "cache_creation.ephemeral_1h_input_tokens" or "cache_creation.ephemeral_5m_input_tokens" or "cache_read_input_tokens" or 2 more`
from line 2207
18792207 - `uncached_input_tokens: number`
18802208
18812209 The number of uncached input tokens processed.
2210
2211### Beta Analytics Usage Cost Inference Geo
2212
2213- `BetaAnalyticsUsageCostInferenceGeo = "global" or "us"`
2214
2215 - `"global"`
2216
2217 - `"us"`
2218
2219### Beta Analytics Usage Cost Product Filter
2220
2221- `BetaAnalyticsUsageCostProductFilter = "chat" or "chat_cowork_unified" or "claude_code" or 9 more`
2222
2223 Publicly documented product surfaces. `claude_tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified.
2224
2225 - `"chat"`
2226
2227 - `"chat_cowork_unified"`
2228
2229 - `"claude_code"`
2230
2231 - `"claude_console"`
2232
2233 - `"claude_design"`
2234
2235 - `"claude_in_chrome"`
2236
2237 - `"claude_tag"`
2238
2239 - `"cowork"`
2240
2241 - `"managed_agents_api"`
2242
2243 - `"message_batches_api"`
2244
2245 - `"messages_api"`
2246
2247 - `"office_agent"`
2248
2249### Beta Analytics Usage Cost Sort Order
2250
2251- `BetaAnalyticsUsageCostSortOrder = "asc" or "desc"`
2252
2253 - `"asc"`
2254
2255 - `"desc"`
18822256
18832257### Beta Analytics Usage Report Time Bucket
18842258
from line 5031
46575031}
46585032```
46595033
5034## Analytics › Usage
5035
5036### Get Token Usage By Dimension
5037
5038**GET** `/v1/organizations/analytics/usage`
5039
5040Get token usage across a date range, broken out by dimension.
5041
5042Returns one row per combination of the requested `group_by[]`
5043dimensions (and time bucket, when `time_bucket_width` is set) that has
5044usage in the range, ranked by the `order_by` metric or ordered by time
5045bucket; every combination is returned across pages. With no `group_by[]`
5046and no `time_bucket_width`, a single row aggregates the whole range.
5047Includes all usage, whether or not it is attributable to a seat user.
5048Requires an API key with the `read:analytics` scope, or an Admin API key.
5049
5050#### Query parameters
5051
5052- `starting_at: string`
5053
5054 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.
5055
5056 format: date-time
5057
5058- `actor_ids: optional array of string`
5059
5060 Filter to usage attributed to specific identities, by tagged ID: a `user_...`, `svac_...` (service account), or `apikey_...` ID. An `apikey_` entry matches only usage attributed to the key itself, not usage on that key attributed to a user or service account (use `api_key_ids[]` for every request a key authenticated). Federated identities have no tagged ID; select them with `actor_types[]`. Use `group_by[]=actor` to break out per-identity values.
5061
5062 maxItems: 100
5063
5064- `actor_types: optional array of BetaAnalyticsActorType`
5065
5066 Filter to usage attributed to specific kinds of identity. Use `group_by[]=actor_type` to break out per-kind values.
5067
5068 maxItems: 100
5069
5070 - `"api_actor"`
5071
5072 - `"federated_actor"`
5073
5074 - `"service_account_actor"`
5075
5076 - `"user_actor"`
5077
5078- `agent_ids: optional array of string`
5079
5080 Filter to usage incurred by sessions of specific Claude Managed Agents agents. Use `group_by[]=agent_id` to break out per-agent values. Claude Developer Platform organizations only.
5081
5082 maxItems: 100
5083
5084- `api_key_ids: optional array of string`
5085
5086 Filter to usage authenticated by specific API keys, by tagged API key ID (`apikey_...`), whichever identity the usage is attributed to. Include an empty entry (`api_key_ids[]=`) to also match usage that no API key authenticated. Use `group_by[]=api_key_id` to break out per-key values; usage without a key has a null `api_key_id`. Claude Developer Platform organizations only.
5087
5088 maxItems: 100
5089
5090- `claude_tag_categories: optional array of BetaAnalyticsClaudeTagCategory`
5091
5092 Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude_tag`, so combining this filter with `products[]=claude_tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values.
5093
5094 maxItems: 100
5095
5096 - `"dm"`
5097
5098 - `"engaged"`
5099
5100 - `"monitoring"`
5101
5102 - `"proactive"`
5103
5104 - `"scheduled"`
5105
5106- `claude_tag_user_ids: optional array of string`
5107
5108 Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values.
5109
5110 maxItems: 100
5111
5112- `context_windows: optional array of BetaAnalyticsContextWindow`
5113
5114 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.
5115
5116 maxItems: 100
5117
5118 - `"0-200k"`
5119
5120 - `"200k-1M"`
5121
5122- `deployment_ids: optional array of string`
5123
5124 Filter to usage incurred by Claude Managed Agents sessions that specific deployments started. Use `group_by[]=deployment_id` to break out per-deployment values. Claude Developer Platform organizations only.
5125
5126 maxItems: 100
5127
5128- `ending_at: optional string`
5129
5130 End of range, exclusive. Required when `time_bucket_width` is set. Without `time_bucket_width`, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.
5131
5132 format: date-time
5133
5134- `environment_ids: optional array of string`
5135
5136 Filter to usage incurred by Claude Managed Agents sessions that ran in specific environments. Use `group_by[]=environment_id` to break out per-environment values. Claude Developer Platform organizations only.
5137
5138 maxItems: 100
5139
5140- `exclude_deleted_users: optional boolean`
5141
5142 If true, omit rows whose `actor` is a `user_actor` with `deleted: true`. Requires `group_by[]=actor`. Rows for other actor types, and rows whose `actor` is null, are always kept. A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual.
5143
5144 default: false
5145
5146- `group_by: optional array of BetaAnalyticsUsageGroupBy`
5147
5148 Dimensions to break usage out by (at most 5): one row per combination of their values with usage in the range (and per time bucket, when `time_bucket_width` is set), every combination returned across pages rather than a capped top set. When omitted, a single row aggregates the whole range.
5149
5150 maxItems: 100
5151
5152 - `"actor"`
5153
5154 - `"actor_type"`
5155
5156 - `"agent_id"`
5157
5158 - `"api_key_id"`
5159
5160 - `"claude_tag_category"`
5161
5162 - `"claude_tag_user_id"`
5163
5164 - `"context_window"`
5165
5166 - `"deployment_id"`
5167
5168 - `"environment_id"`
5169
5170 - `"inference_geo"`
5171
5172 - `"model"`
5173
5174 - `"product"`
5175
5176 - `"rbac_group_id"`
5177
5178 - `"service_tier"`
5179
5180 - `"session_id"`
5181
5182 - `"slack_channel_id"`
5183
5184 - `"speed"`
5185
5186 - `"user_profile_id"`
5187
5188 - `"workspace_id"`
5189
5190- `inference_geos: optional array of BetaAnalyticsInferenceGeoFilter`
5191
5192 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.
5193
5194 maxItems: 100
5195
5196 - `"global"`
5197
5198 - `"not_available"`
5199
5200 - `"us"`
5201
5202- `limit: optional number`
5203
5204 Number of rows per page (1-1000, default 20). `cost_type`/`token_type` fan-out rows (cost endpoint only) do not count toward this limit, so `data` can exceed it.
5205
5206 default: 20, minimum: 1, maximum: 1000
5207
5208- `models: optional array of string`
5209
5210 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.
5211
5212 maxItems: 100
5213
5214- `order: optional BetaAnalyticsUsageCostSortOrder`
5215
5216 Sort direction of the `order_by` metric, or of the time buckets when `order_by` is `time` and `time_bucket_width` is set. Defaults to `desc`.
5217
5218 - `"asc"`
5219
5220 - `"desc"`
5221
5222- `order_by: optional BetaAnalyticsUsageOrderBy`
5223
5224 Row order. A metric ranks rows by that metric in the `order` direction. `time` orders rows by time bucket in the `order` direction (newest first by default) and, within a bucket, by `total_tokens`, highest first. `time` takes effect only with `time_bucket_width`; without it, `time` is the same as `total_tokens`. Defaults to `total_tokens`.
5225
5226 - `"output_tokens"`
5227
5228 - `"requests"`
5229
5230 - `"time"`
5231
5232 - `"total_tokens"`
5233
5234 - `"uncached_input_tokens"`
5235
5236- `page: optional string`
5237
5238 Opaque cursor from a previous response's `next_page` field.
5239
5240- `products: optional array of BetaAnalyticsUsageCostProductFilter`
5241
5242 Product surfaces to include. Defaults to all products.
5243
5244 maxItems: 100
5245
5246 - `"chat"`
5247
5248 - `"chat_cowork_unified"`
5249
5250 - `"claude_code"`
5251
5252 - `"claude_console"`
5253
5254 - `"claude_design"`
5255
5256 - `"claude_in_chrome"`
5257
5258 - `"claude_tag"`
5259
5260 - `"cowork"`
5261
5262 - `"managed_agents_api"`
5263
5264 - `"message_batches_api"`
5265
5266 - `"messages_api"`
5267
5268 - `"office_agent"`
5269
5270- `rbac_group_ids: optional array of string`
5271
5272 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.
5273
5274 maxItems: 100
5275
5276- `service_tiers: optional array of BetaAnalyticsServiceTier`
5277
5278 Filter to specific service tiers. Use `group_by[]=service_tier` to break out per-tier values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization.
5279
5280 maxItems: 100
5281
5282 - `"batch"`
5283
5284 - `"flex"`
5285
5286 - `"flex_discount"`
5287
5288 - `"priority"`
5289
5290 - `"priority_on_demand"`
5291
5292 - `"standard"`
5293
5294- `session_ids: optional array of string`
5295
5296 Filter to usage incurred by specific Claude Managed Agents sessions, by tagged session ID (`sesn_...`). Use `group_by[]=session_id` to break out per-session values. Claude Developer Platform organizations only.
5297
5298 maxItems: 100
5299
5300- `slack_channel_ids: optional array of string`
5301
5302 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.
5303
5304 maxItems: 100
5305
5306- `speeds: optional array of BetaAnalyticsSpeed`
5307
5308 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.
5309
5310 maxItems: 100
5311
5312 - `"fast"`
5313
5314 - `"standard"`
5315
5316- `time_bucket_width: optional BetaAnalyticsTimeBucketWidth`
5317
5318 Time-bucket granularity. When set, rows are returned per time bucket (one per bucket and dimension combination with usage) and each row's `starting_at` and `ending_at` are that bucket's bounds; the time bucket counts toward `limit`. `ending_at` is required when `time_bucket_width` is set, and with `time_bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the requested range with `starting_at` and `ending_at` each rounded down to the hour.
5319
5320 - `"1d"`
5321
5322 - `"1h"`
5323
5324 - `"1m"`
5325
5326- `user_profile_ids: optional array of string`
5327
5328 Filter to usage attributed to specific user profiles, by tagged user profile ID (`uprof_...`). Use `group_by[]=user_profile_id` to break out per-profile values. Claude Developer Platform organizations only.
5329
5330 maxItems: 100
5331
5332- `workspace_ids: optional array of string`
5333
5334 Filter to usage in specific workspaces, by tagged workspace ID (`wrkspc_...`). Use `group_by[]=workspace_id` to break out per-workspace values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization.
5335
5336 maxItems: 100
5337
5338#### Headers
5339
5340- `"anthropic-version": optional string`
5341
5342 The version of the Claude API you want to use.
5343
5344 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning?sdk_languages=http).
5345
5346- `"anthropic-beta": optional array of AnthropicBeta`
5347
5348 This endpoint is in beta: requests must send `analytics-usage-cost-2026-08-24` in this header.
5349
5350 - `string`
5351
5352 - `"message-batches-2024-09-24"`
5353
5354 - `"prompt-caching-2024-07-31"`
5355
5356 - `"computer-use-2024-10-22"`
5357
5358 - `"computer-use-2025-01-24"`
5359
5360 - `"pdfs-2024-09-25"`
5361
5362 - `"token-counting-2024-11-01"`
5363
5364 - `"token-efficient-tools-2025-02-19"`
5365
5366 - `"output-128k-2025-02-19"`
5367
5368 - `"files-api-2025-04-14"`
5369
5370 - `"mcp-client-2025-04-04"`
5371
5372 - `"mcp-client-2025-11-20"`
5373
5374 - `"dev-full-thinking-2025-05-14"`
5375
5376 - `"interleaved-thinking-2025-05-14"`
5377
5378 - `"code-execution-2025-05-22"`
5379
5380 - `"extended-cache-ttl-2025-04-11"`
5381
5382 - `"context-1m-2025-08-07"`
5383
5384 - `"context-management-2025-06-27"`
5385
5386 - `"model-context-window-exceeded-2025-08-26"`
5387
5388 - `"skills-2025-10-02"`
5389
5390 - `"fast-mode-2026-02-01"`
5391
5392 - `"output-300k-2026-03-24"`
5393
5394 - `"user-profiles-2026-03-24"`
5395
5396 - `"user-profiles-2026-08-18"`
5397
5398 - `"user-profiles-2026-09-04"`
5399
5400 - `"advisor-tool-2026-03-01"`
5401
5402 - `"managed-agents-2026-04-01"`
5403
5404 - `"cache-diagnosis-2026-04-07"`
5405
5406 - `"dreaming-2026-04-21"`
5407
5408 - `"thinking-token-count-2026-05-13"`
5409
5410 - `"server-side-fallback-2026-06-01"`
5411
5412 - `"server-side-fallback-2026-07-01"`
5413
5414 - `"fallback-credit-2026-06-01"`
5415
5416 - `"fallback-credit-2026-07-01"`
5417
5418 - `"agent-memory-2026-07-22"`
5419
5420 - `"mid-conversation-tool-changes-2026-07-01"`
5421
5422 - `"compact-2026-01-12"`
5423
5424 - `"computer-use-2025-11-24"`
5425
5426 - `"mcp-tunnels-2026-06-22"`
5427
5428 - `"structured-outputs-2025-11-13"`
5429
5430 - `"task-budgets-2026-03-13"`
5431
5432 - `"thinking-display-updates-2026-08-18"`
5433
5434 - `"ce-user-management-2026-07-13"`
5435
5436 - `"mid-conversation-output-config-2026-07-01"`
5437
5438 - `"thinking-binding-controls-2026-08-01"`
5439
5440 - `"mid-conversation-system-clear-at-2026-08-21"`
5441
5442 - `"compact-2026-09-04"`
5443
5444 - `"inline-tools-2026-09-15"`
5445
5446 - `"mcp-client-2026-09-15"`
5447
5448 - `"ce-plugins-2026-09-01"`
5449
5450 - `"spend-limit-reads-2026-09-26"`
5451
5452 - `"telemetry-destinations-2026-08-11"`
5453
5454 - `"webhooks-2026-10-07"`
5455
5456 - `"message-threads-2026-08-12"`
5457
5458 - `"analytics-usage-cost-2026-08-24"`
5459
5460#### Returns
5461
5462- `data: array of BetaAnalyticsUsageItem`
5463
5464 Rows for this page, in the order set by `order_by` and `order`: one per combination of the `group_by[]` dimensions (and per time bucket, when `time_bucket_width` is set) with usage or cost in the range, or a single row when neither is set. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.
5465
5466 - `ending_at: string`
5467
5468 End of the period this row covers (exclusive), as an RFC 3339 UTC timestamp: the end of the row's time bucket when a time-bucket width is set; otherwise the requested `ending_at` (or, when omitted, the earlier of now and `starting_at` plus 31 days) rounded down to the hour, because without a time bucket the report covers whole hours.
5469
5470 format: date-time
5471
5472 - `group: BetaAnalyticsUsageGroup`
5473
5474 The dimension values this row's usage is broken out by.
5475
5476 - `actor: BetaAnalyticsActor or null`
5477
5478 The identity the usage is attributed to: the user if one is attributed, else the service account, else the federated (cloud-platform) identity, else the API key. Populated only when `actor` is in `group_by[]`; null for usage with no attributable identity, and for users' and federated identities' usage when the reader is a member who can see only some workspaces. Distinct identities the server cannot render also read null, each as its own row.
5479
5480 - `BetaAnalyticsReportUserActor object`
5481
5482 - `type: "user_actor"`
5483
5484 Actor type. Always `"user_actor"`.
5485
5486 - `deleted: boolean`
5487
5488 True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation.
5489
5490 - `email_address: string or null`
5491
5492 The user's current email address, including for users who are no longer members of the organization. Null when the account has been deleted and for system-minted service accounts.
5493
5494 - `name: string or null`
5495
5496 The user's current full name. Null when the user has not set one. `"Deleted User"` when the account has been deleted, or when the user is no longer a member and the organization hides removed users' names.
5497
5498 - `user_id: string`
5499
5500 Tagged user ID.
5501
5502 - `BetaAnalyticsServiceAccountActor object`
5503
5504 - `type: "service_account_actor"`
5505
5506 - `service_account_id: string`
5507
5508 Tagged service account ID.
5509
5510 - `BetaAnalyticsFederatedActor object`
5511
5512 - `type: "federated_actor"`
5513
5514 - `provider: BetaAnalyticsFederatedActorProvider`
5515
5516 The trusted provider that asserted the caller's identity.
5517
5518 - `BetaAnalyticsFederatedActorAWSProvider object`
5519
5520 - `type: "aws"`
5521
5522 - `account_id: string`
5523
5524 The AWS account the organization is bound to.
5525
5526 - `signed_principal: string`
5527
5528 The AWS-signed ARN of the IAM principal that made the requests.
5529
5530 - `BetaAnalyticsFederatedActorAzureProvider object`
5531
5532 - `type: "azure"`
5533
5534 - `subscription_id: string`
5535
5536 The Azure subscription the organization is bound to.
5537
5538 - `BetaAnalyticsFederatedActorGCPProvider object`
5539
5540 - `type: "gcp"`
5541
5542 - `project_number: string`
5543
5544 The Google Cloud project the organization is bound to.
5545
5546 - `BetaAnalyticsFederatedActorOIDCProvider object`
5547
5548 - `type: "oidc"`
5549
5550 - `issuer: string or null`
5551
5552 The federation issuer's URL.
5553
5554 - `subject: string or null`
5555
5556 The provider's identifier for the caller: on `aws`, the IAM principal ARN (one role is one actor across its sessions); on `gcp`, the caller's IAM principal identifier as Google Cloud reports it, such as `serviceAccount:<email>`, `user:<email>`, or a `principal://...` URI.
5557
5558 - `BetaAnalyticsAPIActor object`
5559
5560 - `type: "api_actor"`
5561
5562 - `api_key_id: string`
5563
5564 Tagged API key ID.
5565
5566 - `actor_type: BetaAnalyticsActorType or null`
5567
5568 Kind of identity the usage is attributed to; matches `actor.type` when `actor` is set. Populated only when `actor_type` is in `group_by[]`.
5569
5570 - `"api_actor"`
5571
5572 - `"federated_actor"`
5573
5574 - `"service_account_actor"`
5575
5576 - `"user_actor"`
5577
5578 - `agent_id: string or null`
5579
5580 Claude Managed Agents agent whose session incurred the usage. Populated only when `agent_id` is in `group_by[]`; null for usage outside a managed session.
5581
5582 - `api_key_id: string or null`
5583
5584 API key that authenticated the requests, as a tagged API key ID, whichever identity `actor` resolves to. Populated only when `api_key_id` is in `group_by[]`; null for usage not authenticated by an API key.
5585
5586 - `claude_tag_category: BetaAnalyticsClaudeTagCategory or null`
5587
5588 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude_tag`. New categories may be added over time.
5589
5590 - `"dm"`
5591
5592 - `"engaged"`
5593
5594 - `"monitoring"`
5595
5596 - `"proactive"`
5597
5598 - `"scheduled"`
5599
5600 - `claude_tag_user_id: string or null`
5601
5602 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
5603
5604 - `context_window: BetaAnalyticsContextWindow or null`
5605
5606 Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution.
5607
5608 - `"0-200k"`
5609
5610 - `"200k-1M"`
5611
5612 - `deployment_id: string or null`
5613
5614 Deployment that started the Claude Managed Agents session. Populated only when `deployment_id` is in `group_by[]`; null for usage outside a managed session and for sessions no deployment started.
5615
5616 - `environment_id: string or null`
5617
5618 Claude Managed Agents environment the session ran in. Populated only when `environment_id` is in `group_by[]`; null for usage outside a managed session.
5619
5620 - `inference_geo: BetaAnalyticsUsageCostInferenceGeo or null`
5621
5622 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).
5623
5624 - `"global"`
5625
5626 - `"us"`
5627
5628 - `model: string or null`
5629
5630 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.
5631
5632 - `product: string or null`
5633
5634 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude_tag`, and `chat_cowork_unified`. `claude_tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other".
5635
5636 - `rbac_group_id: string or null`
5637
5638 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`.
5639
5640 - `service_tier: BetaAnalyticsServiceTier or null`
5641
5642 Service tier the usage was served at. Populated only when `service_tier` is in `group_by[]`; null for usage with no service tier (for example, code execution) and for Claude Enterprise usage.
5643
5644 - `"batch"`
5645
5646 - `"flex"`
5647
5648 - `"flex_discount"`
5649
5650 - `"priority"`
5651
5652 - `"priority_on_demand"`
5653
5654 - `"standard"`
5655
5656 - `session_id: string or null`
5657
5658 Claude Managed Agents session that incurred the usage. Populated only when `session_id` is in `group_by[]`; null for usage outside a managed session.
5659
5660 - `slack_channel_id: string or null`
5661
5662 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).
5663
5664 - `speed: BetaAnalyticsSpeed or null`
5665
5666 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.
5667
5668 - `"fast"`
5669
5670 - `"standard"`
5671
5672 - `user_profile_id: string or null`
5673
5674 User profile the usage was attributed to, as a tagged `uprof_` ID. Populated only when `user_profile_id` is in `group_by[]`; null for usage that named no profile and for Claude Enterprise usage.
5675
5676 - `workspace_id: string or null`
5677
5678 Workspace the usage occurred in, as a tagged workspace ID, including the organization's default workspace. Populated only when `workspace_id` is in `group_by[]`; null for Claude Enterprise usage.
5679
5680 - `starting_at: string`
5681
5682 Start of the period this row covers (inclusive), as an RFC 3339 UTC timestamp: the start of the row's time bucket when a time-bucket width is set, otherwise the requested `starting_at` rounded down to the hour.
5683
5684 format: date-time
5685
5686 - `usage: BetaAnalyticsUsageMetrics`
5687
5688 Token usage for this row.
5689
5690 - `cache_creation: BetaCacheCreation`
5691
5692 The number of input tokens for cache creation.
5693
5694 - `ephemeral_1h_input_tokens: number`
5695
5696 The number of input tokens used to create the 1 hour cache entry.
5697
5698 default: 0, minimum: 0
5699
5700 - `ephemeral_5m_input_tokens: number`
5701
5702 The number of input tokens used to create the 5 minute cache entry.
5703
5704 default: 0, minimum: 0
5705
5706 - `cache_read_input_tokens: number`
5707
5708 The number of input tokens read from the cache.
5709
5710 - `output_tokens: number`
5711
5712 The number of output tokens generated.
5713
5714 - `requests: number or null`
5715
5716 Number of API requests in this row's scope. For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).
5717
5718 - `server_tool_use: BetaAnalyticsServerToolUse`
5719
5720 Server-side tool usage metrics.
5721
5722 - `web_search_requests: number`
5723
5724 The number of web search requests made.
5725
5726 - `total_tokens: number`
5727
5728 Total token count across all token types. This is the value the default `order_by` (`total_tokens`) sorts on.
5729
5730 - `uncached_input_tokens: number`
5731
5732 The number of uncached input tokens processed.
5733
5734- `data_refreshed_at: string or null`
5735
5736 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours. Values can be revised as late events arrive and reconciliation runs, until about 7 days after the end of the calendar month the usage falls in; for example, values for October 1 can change until about November 7.
5737
5738 format: date-time
5739
5740- `has_more: boolean`
5741
5742 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.
5743
5744- `next_page: string or null`
5745
5746 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.
5747
5748#### Example
5749
5750```bash
5751curl https://api.anthropic.com/v1/organizations/analytics/usage \
5752 -H 'anthropic-version: 2026-10-21' \
5753 -H 'anthropic-beta: analytics-usage-cost-2026-08-24' \
5754 -H "Authorization: Bearer $ANTHROPIC_API_KEY"
5755```
5756
5757##### Response (200)
5758
5759```json
5760{
5761 "data": [
5762 {
5763 "ending_at": "2026-10-01T00:00:00Z",
5764 "group": {
5765 "actor": {
5766 "deleted": false,
5767 "email_address": "[email protected]",
5768 "name": "Jane Doe",
5769 "type": "user_actor",
5770 "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q"
5771 },
5772 "actor_type": "user_actor",
5773 "agent_id": "agent_01VHd3EAGJ6PLkP9LM7DDu3f",
5774 "api_key_id": "apikey_01Rj2N8SVvo6BePZj99NhmiT",
5775 "claude_tag_category": "dm",
5776 "claude_tag_user_id": "U0123ABCDEF",
5777 "context_window": "0-200k",
5778 "deployment_id": "depl_01JFC6ihzZHtAuyHsaENdJhY",
5779 "environment_id": "env_017oTjuGedHtjhJauVC5xGJD",
5780 "inference_geo": "global",
5781 "model": "claude-opus-5-5",
5782 "product": "chat",
5783 "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF",
5784 "service_tier": "standard",
5785 "session_id": "sesn_0187kPDyNCwibNNvfaPEApCJ",
5786 "slack_channel_id": "C0123ABCDEF",
5787 "speed": "fast",
5788 "user_profile_id": "uprof_01M33NeYUQK2WV9PpYcsPHLi",
5789 "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ"
5790 },
5791 "starting_at": "2026-09-01T00:00:00Z",
5792 "usage": {
5793 "cache_creation": {
5794 "ephemeral_1h_input_tokens": 0,
5795 "ephemeral_5m_input_tokens": 0
5796 },
5797 "cache_read_input_tokens": 3200000,
5798 "output_tokens": 891000,
5799 "requests": 128,
5800 "server_tool_use": {
5801 "web_search_requests": 10
5802 },
5803 "total_tokens": 5377000,
5804 "uncached_input_tokens": 1284500
5805 }
5806 }
5807 ],
5808 "data_refreshed_at": "2019-12-27T18:11:19.117Z",
5809 "has_more": true,
5810 "next_page": "next_page"
5811}
5812```
5813
5814## Analytics › Cost
5815
5816### Get Cost By Dimension
5817
5818**GET** `/v1/organizations/analytics/cost`
5819
5820Get cost in USD across a date range, broken out by dimension.
5821
5822Returns one row per combination of the requested `group_by[]`
5823dimensions (and time bucket, when `time_bucket_width` is set) that has
5824cost in the range, ranked by spend or ordered by time bucket; every
5825combination is returned across pages. With no `group_by[]` and no
5826`time_bucket_width`, a single row aggregates the whole range. Includes
5827all cost, whether or not it is attributable to a seat user. Requires an
5828API key with the `read:analytics` scope, or an Admin API key.
5829
5830#### Query parameters
5831
5832- `starting_at: string`
5833
5834 Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z.
5835
5836 format: date-time
5837
5838- `actor_ids: optional array of string`
5839
5840 Filter to usage attributed to specific identities, by tagged ID: a `user_...`, `svac_...` (service account), or `apikey_...` ID. An `apikey_` entry matches only usage attributed to the key itself, not usage on that key attributed to a user or service account (use `api_key_ids[]` for every request a key authenticated). Federated identities have no tagged ID; select them with `actor_types[]`. Use `group_by[]=actor` to break out per-identity values.
5841
5842 maxItems: 100
5843
5844- `actor_types: optional array of BetaAnalyticsActorType`
5845
5846 Filter to usage attributed to specific kinds of identity. Use `group_by[]=actor_type` to break out per-kind values.
5847
5848 maxItems: 100
5849
5850 - `"api_actor"`
5851
5852 - `"federated_actor"`
5853
5854 - `"service_account_actor"`
5855
5856 - `"user_actor"`
5857
5858- `agent_ids: optional array of string`
5859
5860 Filter to usage incurred by sessions of specific Claude Managed Agents agents. Use `group_by[]=agent_id` to break out per-agent values. Claude Developer Platform organizations only.
5861
5862 maxItems: 100
5863
5864- `api_key_ids: optional array of string`
5865
5866 Filter to usage authenticated by specific API keys, by tagged API key ID (`apikey_...`), whichever identity the usage is attributed to. Include an empty entry (`api_key_ids[]=`) to also match usage that no API key authenticated. Use `group_by[]=api_key_id` to break out per-key values; usage without a key has a null `api_key_id`. Claude Developer Platform organizations only.
5867
5868 maxItems: 100
5869
5870- `claude_tag_categories: optional array of BetaAnalyticsClaudeTagCategory`
5871
5872 Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude_tag`, so combining this filter with `products[]=claude_tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values.
5873
5874 maxItems: 100
5875
5876 - `"dm"`
5877
5878 - `"engaged"`
5879
5880 - `"monitoring"`
5881
5882 - `"proactive"`
5883
5884 - `"scheduled"`
5885
5886- `claude_tag_user_ids: optional array of string`
5887
5888 Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values.
5889
5890 maxItems: 100
5891
5892- `context_windows: optional array of BetaAnalyticsContextWindow`
5893
5894 Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values.
5895
5896 maxItems: 100
5897
5898 - `"0-200k"`
5899
5900 - `"200k-1M"`
5901
5902- `deployment_ids: optional array of string`
5903
5904 Filter to usage incurred by Claude Managed Agents sessions that specific deployments started. Use `group_by[]=deployment_id` to break out per-deployment values. Claude Developer Platform organizations only.
5905
5906 maxItems: 100
5907
5908- `ending_at: optional string`
5909
5910 End of range, exclusive. Required when `time_bucket_width` is set. Without `time_bucket_width`, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days.
5911
5912 format: date-time
5913
5914- `environment_ids: optional array of string`
5915
5916 Filter to usage incurred by Claude Managed Agents sessions that ran in specific environments. Use `group_by[]=environment_id` to break out per-environment values. Claude Developer Platform organizations only.
5917
5918 maxItems: 100
5919
5920- `exclude_deleted_users: optional boolean`
5921
5922 If true, omit rows whose `actor` is a `user_actor` with `deleted: true`. Requires `group_by[]=actor`. Rows for other actor types, and rows whose `actor` is null, are always kept. A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual.
5923
5924 default: false
5925
5926- `group_by: optional array of BetaAnalyticsCostGroupBy`
5927
5928 Dimensions to break cost out by (at most 5, not counting `cost_type` and `token_type`): one row per combination of their values with cost in the range (and per time bucket, when `time_bucket_width` is set), every combination returned across pages rather than a capped top set. `cost_type` and `token_type` do not count toward `limit`: `cost_type` returns one row per cost component (tokens, web search, code execution, and `session_usage`, Claude Managed Agents session time); `token_type` returns one row per token type, each with `cost_type: "tokens"`; combining both returns the per-token-type rows plus the web-search, code-execution and session-usage rows. When omitted, a single row aggregates the whole range.
5929
5930 maxItems: 100
5931
5932 - `"actor"`
5933
5934 - `"actor_type"`
5935
5936 - `"agent_id"`
5937
5938 - `"api_key_id"`
5939
5940 - `"claude_tag_category"`
5941
5942 - `"claude_tag_user_id"`
5943
5944 - `"context_window"`
5945
5946 - `"cost_type"`
5947
5948 - `"deployment_id"`
5949
5950 - `"environment_id"`
5951
5952 - `"inference_geo"`
5953
5954 - `"model"`
5955
5956 - `"product"`
5957
5958 - `"rbac_group_id"`
5959
5960 - `"service_tier"`
5961
5962 - `"session_id"`
5963
5964 - `"slack_channel_id"`
5965
5966 - `"speed"`
5967
5968 - `"token_type"`
5969
5970 - `"user_profile_id"`
5971
5972 - `"workspace_id"`
5973
5974- `inference_geos: optional array of BetaAnalyticsInferenceGeoFilter`
5975
5976 Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values.
5977
5978 maxItems: 100
5979
5980 - `"global"`
5981
5982 - `"not_available"`
5983
5984 - `"us"`
5985
5986- `limit: optional number`
5987
5988 Number of rows per page (1-1000, default 20). `cost_type`/`token_type` fan-out rows (cost endpoint only) do not count toward this limit, so `data` can exceed it.
5989
5990 default: 20, minimum: 1, maximum: 1000
5991
5992- `models: optional array of string`
5993
5994 Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values.
5995
5996 maxItems: 100
5997
5998- `order: optional BetaAnalyticsUsageCostSortOrder`
5999
6000 Sort direction of the `order_by` metric, or of the time buckets when `order_by` is `time` and `time_bucket_width` is set. Defaults to `desc`.
6001
6002 - `"asc"`
6003
6004 - `"desc"`
6005
6006- `order_by: optional BetaAnalyticsCostOrderBy`
6007
6008 Row order. A metric ranks rows by that metric in the `order` direction. `time` orders rows by time bucket in the `order` direction (newest first by default) and, within a bucket, by `amount`, highest first. `time` takes effect only with `time_bucket_width`; without it, `time` is the same as `amount`. Defaults to `amount`.
6009
6010 - `"amount"`
6011
6012 - `"list_amount"`
6013
6014 - `"time"`
6015
6016- `page: optional string`
6017
6018 Opaque cursor from a previous response's `next_page` field.
6019
6020- `products: optional array of BetaAnalyticsUsageCostProductFilter`
6021
6022 Product surfaces to include. Defaults to all products.
6023
6024 maxItems: 100
6025
6026 - `"chat"`
6027
6028 - `"chat_cowork_unified"`
6029
6030 - `"claude_code"`
6031
6032 - `"claude_console"`
6033
6034 - `"claude_design"`
6035
6036 - `"claude_in_chrome"`
6037
6038 - `"claude_tag"`
6039
6040 - `"cowork"`
6041
6042 - `"managed_agents_api"`
6043
6044 - `"message_batches_api"`
6045
6046 - `"messages_api"`
6047
6048 - `"office_agent"`
6049
6050- `rbac_group_ids: optional array of string`
6051
6052 Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches.
6053
6054 maxItems: 100
6055
6056- `service_tiers: optional array of BetaAnalyticsServiceTier`
6057
6058 Filter to specific service tiers. Use `group_by[]=service_tier` to break out per-tier values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization.
6059
6060 maxItems: 100
6061
6062 - `"batch"`
6063
6064 - `"flex"`
6065
6066 - `"flex_discount"`
6067
6068 - `"priority"`
6069
6070 - `"priority_on_demand"`
6071
6072 - `"standard"`
6073
6074- `session_ids: optional array of string`
6075
6076 Filter to usage incurred by specific Claude Managed Agents sessions, by tagged session ID (`sesn_...`). Use `group_by[]=session_id` to break out per-session values. Claude Developer Platform organizations only.
6077
6078 maxItems: 100
6079
6080- `slack_channel_ids: optional array of string`
6081
6082 Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values.
6083
6084 maxItems: 100
6085
6086- `speeds: optional array of BetaAnalyticsSpeed`
6087
6088 Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values.
6089
6090 maxItems: 100
6091
6092 - `"fast"`
6093
6094 - `"standard"`
6095
6096- `time_bucket_width: optional BetaAnalyticsTimeBucketWidth`
6097
6098 Time-bucket granularity. When set, rows are returned per time bucket (one per bucket and dimension combination with usage) and each row's `starting_at` and `ending_at` are that bucket's bounds; the time bucket counts toward `limit`. `ending_at` is required when `time_bucket_width` is set, and with `time_bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the requested range with `starting_at` and `ending_at` each rounded down to the hour.
6099
6100 - `"1d"`
6101
6102 - `"1h"`
6103
6104 - `"1m"`
6105
6106- `user_profile_ids: optional array of string`
6107
6108 Filter to usage attributed to specific user profiles, by tagged user profile ID (`uprof_...`). Use `group_by[]=user_profile_id` to break out per-profile values. Claude Developer Platform organizations only.
6109
6110 maxItems: 100
6111
6112- `workspace_ids: optional array of string`
6113
6114 Filter to usage in specific workspaces, by tagged workspace ID (`wrkspc_...`). Use `group_by[]=workspace_id` to break out per-workspace values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization.
6115
6116 maxItems: 100
6117
6118#### Headers
6119
6120- `"anthropic-version": optional string`
6121
6122 The version of the Claude API you want to use.
6123
6124 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning?sdk_languages=http).
6125
6126- `"anthropic-beta": optional array of AnthropicBeta`
6127
6128 This endpoint is in beta: requests must send `analytics-usage-cost-2026-08-24` in this header.
6129
6130 - `string`
6131
6132 - `"message-batches-2024-09-24"`
6133
6134 - `"prompt-caching-2024-07-31"`
6135
6136 - `"computer-use-2024-10-22"`
6137
6138 - `"computer-use-2025-01-24"`
6139
6140 - `"pdfs-2024-09-25"`
6141
6142 - `"token-counting-2024-11-01"`
6143
6144 - `"token-efficient-tools-2025-02-19"`
6145
6146 - `"output-128k-2025-02-19"`
6147
6148 - `"files-api-2025-04-14"`
6149
6150 - `"mcp-client-2025-04-04"`
6151
6152 - `"mcp-client-2025-11-20"`
6153
6154 - `"dev-full-thinking-2025-05-14"`
6155
6156 - `"interleaved-thinking-2025-05-14"`
6157
6158 - `"code-execution-2025-05-22"`
6159
6160 - `"extended-cache-ttl-2025-04-11"`
6161
6162 - `"context-1m-2025-08-07"`
6163
6164 - `"context-management-2025-06-27"`
6165
6166 - `"model-context-window-exceeded-2025-08-26"`
6167
6168 - `"skills-2025-10-02"`
6169
6170 - `"fast-mode-2026-02-01"`
6171
6172 - `"output-300k-2026-03-24"`
6173
6174 - `"user-profiles-2026-03-24"`
6175
6176 - `"user-profiles-2026-08-18"`
6177
6178 - `"user-profiles-2026-09-04"`
6179
6180 - `"advisor-tool-2026-03-01"`
6181
6182 - `"managed-agents-2026-04-01"`
6183
6184 - `"cache-diagnosis-2026-04-07"`
6185
6186 - `"dreaming-2026-04-21"`
6187
6188 - `"thinking-token-count-2026-05-13"`
6189
6190 - `"server-side-fallback-2026-06-01"`
6191
6192 - `"server-side-fallback-2026-07-01"`
6193
6194 - `"fallback-credit-2026-06-01"`
6195
6196 - `"fallback-credit-2026-07-01"`
6197
6198 - `"agent-memory-2026-07-22"`
6199
6200 - `"mid-conversation-tool-changes-2026-07-01"`
6201
6202 - `"compact-2026-01-12"`
6203
6204 - `"computer-use-2025-11-24"`
6205
6206 - `"mcp-tunnels-2026-06-22"`
6207
6208 - `"structured-outputs-2025-11-13"`
6209
6210 - `"task-budgets-2026-03-13"`
6211
6212 - `"thinking-display-updates-2026-08-18"`
6213
6214 - `"ce-user-management-2026-07-13"`
6215
6216 - `"mid-conversation-output-config-2026-07-01"`
6217
6218 - `"thinking-binding-controls-2026-08-01"`
6219
6220 - `"mid-conversation-system-clear-at-2026-08-21"`
6221
6222 - `"compact-2026-09-04"`
6223
6224 - `"inline-tools-2026-09-15"`
6225
6226 - `"mcp-client-2026-09-15"`
6227
6228 - `"ce-plugins-2026-09-01"`
6229
6230 - `"spend-limit-reads-2026-09-26"`
6231
6232 - `"telemetry-destinations-2026-08-11"`
6233
6234 - `"webhooks-2026-10-07"`
6235
6236 - `"message-threads-2026-08-12"`
6237
6238 - `"analytics-usage-cost-2026-08-24"`
6239
6240#### Returns
6241
6242- `data: array of BetaAnalyticsCostItem`
6243
6244 Rows for this page, in the order set by `order_by` and `order`: one per combination of the `group_by[]` dimensions (and per time bucket, when `time_bucket_width` is set) with usage or cost in the range, or a single row when neither is set. Rows split out by `cost_type` or `token_type` (cost endpoint only) stay adjacent and are ranked as one unit.
6245
6246 - `cost: BetaAnalyticsCostMetrics`
6247
6248 Cost for this row.
6249
6250 - `amount: string`
6251
6252 Amount (post-discount, pre-credit) in fractional cents (minor units).
6253
6254 - `currency: string`
6255
6256 Currency code for the cost amount. Currently always `"USD"`.
6257
6258 default: USD
6259
6260 - `list_amount: string`
6261
6262 List-price amount (pre-discount) in fractional cents.
6263
6264 - `requests: number or null`
6265
6266 Number of API requests in this row's scope. Null when `group_by` includes `cost_type` or `token_type` (the count has no per-component attribution; read it from the ungrouped response). For sandbox / code-execution events, this counts execution spans rather than HTTP requests (these rows surface with `product: null`).
6267
6268 - `ending_at: string`
6269
6270 End of the period this row covers (exclusive), as an RFC 3339 UTC timestamp: the end of the row's time bucket when a time-bucket width is set; otherwise the requested `ending_at` (or, when omitted, the earlier of now and `starting_at` plus 31 days) rounded down to the hour, because without a time bucket the report covers whole hours.
6271
6272 format: date-time
6273
6274 - `group: BetaAnalyticsCostGroup`
6275
6276 The dimension values this row's cost is broken out by.
6277
6278 - `actor: BetaAnalyticsActor or null`
6279
6280 The identity the usage is attributed to: the user if one is attributed, else the service account, else the federated (cloud-platform) identity, else the API key. Populated only when `actor` is in `group_by[]`; null for usage with no attributable identity, and for users' and federated identities' usage when the reader is a member who can see only some workspaces. Distinct identities the server cannot render also read null, each as its own row.
6281
6282 - `BetaAnalyticsReportUserActor object`
6283
6284 - `type: "user_actor"`
6285
6286 Actor type. Always `"user_actor"`.
6287
6288 - `deleted: boolean`
6289
6290 True when the account has been deleted, or when the user is no longer a member of the organization or its associated organizations (for example, their membership was removed or they were deprovisioned via your identity provider). `email_address` stays populated for removed users and is null when the account has been deleted. `name` follows the rules described on that field. The `user_id` is still populated for reconciliation.
6291
6292 - `email_address: string or null`
6293
6294 The user's current email address, including for users who are no longer members of the organization. Null when the account has been deleted and for system-minted service accounts.
6295
6296 - `name: string or null`
6297
6298 The user's current full name. Null when the user has not set one. `"Deleted User"` when the account has been deleted, or when the user is no longer a member and the organization hides removed users' names.
6299
6300 - `user_id: string`
6301
6302 Tagged user ID.
6303
6304 - `BetaAnalyticsServiceAccountActor object`
6305
6306 - `type: "service_account_actor"`
6307
6308 - `service_account_id: string`
6309
6310 Tagged service account ID.
6311
6312 - `BetaAnalyticsFederatedActor object`
6313
6314 - `type: "federated_actor"`
6315
6316 - `provider: BetaAnalyticsFederatedActorProvider`
6317
6318 The trusted provider that asserted the caller's identity.
6319
6320 - `BetaAnalyticsFederatedActorAWSProvider object`
6321
6322 - `type: "aws"`
6323
6324 - `account_id: string`
6325
6326 The AWS account the organization is bound to.
6327
6328 - `signed_principal: string`
6329
6330 The AWS-signed ARN of the IAM principal that made the requests.
6331
6332 - `BetaAnalyticsFederatedActorAzureProvider object`
6333
6334 - `type: "azure"`
6335
6336 - `subscription_id: string`
6337
6338 The Azure subscription the organization is bound to.
6339
6340 - `BetaAnalyticsFederatedActorGCPProvider object`
6341
6342 - `type: "gcp"`
6343
6344 - `project_number: string`
6345
6346 The Google Cloud project the organization is bound to.
6347
6348 - `BetaAnalyticsFederatedActorOIDCProvider object`
6349
6350 - `type: "oidc"`
6351
6352 - `issuer: string or null`
6353
6354 The federation issuer's URL.
6355
6356 - `subject: string or null`
6357
6358 The provider's identifier for the caller: on `aws`, the IAM principal ARN (one role is one actor across its sessions); on `gcp`, the caller's IAM principal identifier as Google Cloud reports it, such as `serviceAccount:<email>`, `user:<email>`, or a `principal://...` URI.
6359
6360 - `BetaAnalyticsAPIActor object`
6361
6362 - `type: "api_actor"`
6363
6364 - `api_key_id: string`
6365
6366 Tagged API key ID.
6367
6368 - `actor_type: BetaAnalyticsActorType or null`
6369
6370 Kind of identity the usage is attributed to; matches `actor.type` when `actor` is set. Populated only when `actor_type` is in `group_by[]`.
6371
6372 - `"api_actor"`
6373
6374 - `"federated_actor"`
6375
6376 - `"service_account_actor"`
6377
6378 - `"user_actor"`
6379
6380 - `agent_id: string or null`
6381
6382 Claude Managed Agents agent whose session incurred the usage. Populated only when `agent_id` is in `group_by[]`; null for usage outside a managed session.
6383
6384 - `api_key_id: string or null`
6385
6386 API key that authenticated the requests, as a tagged API key ID, whichever identity `actor` resolves to. Populated only when `api_key_id` is in `group_by[]`; null for usage not authenticated by an API key.
6387
6388 - `claude_tag_category: BetaAnalyticsClaudeTagCategory or null`
6389
6390 Claude Tag (Claude in Slack) spend category: `engaged` (a person addressed Claude in a channel or thread), `proactive` (Claude responded without being addressed), `scheduled` (a scheduled routine ran), `monitoring` (Claude watching a channel it was asked to monitor), or `dm` (direct messages with Claude). Populated only when `claude_tag_category` is in `group_by[]`; null for usage that is not Claude Tag. Direct-message usage is billed to the individual user and is reported under that user's product, not under `claude_tag`. New categories may be added over time.
6391
6392 - `"dm"`
6393
6394 - `"engaged"`
6395
6396 - `"monitoring"`
6397
6398 - `"proactive"`
6399
6400 - `"scheduled"`
6401
6402 - `claude_tag_user_id: string or null`
6403
6404 Slack user ID (for example `U0123ABCDEF`) of the member the Claude Tag (Claude in Slack) usage is attributed to, not a claude.ai user ID. Populated only when `claude_tag_user_id` is in `group_by[]`; null for usage that is not Claude Tag and for Claude Tag usage that is not attributed to a single user (for example `monitoring`, and `proactive` usage Claude initiated), so per-user rows can sum to less than the Claude Tag total. Cannot be combined with `group_by[]=rbac_group_id` or the `rbac_group_ids[]` filter.
6405
6406 - `context_window: BetaAnalyticsContextWindow or null`
6407
6408 Context-window pricing tier of the usage or cost. Null unless `context_window` is in `group_by[]`; it can also be null on grouped rows with no context-window tier, such as code execution.
6409
6410 - `"0-200k"`
6411
6412 - `"200k-1M"`
6413
6414 - `cost_type: BetaAnalyticsGroupedCostType or null`
6415
6416 Cost component breakdown; null when returning the combined total.
6417
6418 - `"code_execution"`
6419
6420 - `"session_usage"`
6421
6422 - `"tokens"`
6423
6424 - `"web_search"`
6425
6426 - `deployment_id: string or null`
6427
6428 Deployment that started the Claude Managed Agents session. Populated only when `deployment_id` is in `group_by[]`; null for usage outside a managed session and for sessions no deployment started.
6429
6430 - `environment_id: string or null`
6431
6432 Claude Managed Agents environment the session ran in. Populated only when `environment_id` is in `group_by[]`; null for usage outside a managed session.
6433
6434 - `inference_geo: BetaAnalyticsUsageCostInferenceGeo or null`
6435
6436 Inference region of the usage or cost. Null unless `inference_geo` is in `group_by[]`; it can also be null on grouped rows where the region is not set (the rows that `inference_geos[]=not_available` matches).
6437
6438 - `"global"`
6439
6440 - `"us"`
6441
6442 - `model: string or null`
6443
6444 Model that produced the usage or cost, as a model name in the form the `models[]` filter accepts (for example, `claude-opus-5-5`). Null unless `model` is in `group_by[]`; it can also be null on grouped rows whose usage or cost is not attributed to a specific model, such as code execution.
6445
6446 - `product: string or null`
6447
6448 Product surface that produced the usage or cost. Null unless product is in `group_by[]`; it can also be null on grouped rows whose usage cannot be attributed to a known surface. Values include `chat`, `claude_code`, `cowork`, `office_agent`, `claude_in_chrome`, `claude_design`, `claude_tag`, and `chat_cowork_unified`. `claude_tag` is Claude Tag, the Claude product in Slack. `chat_cowork_unified` is Chat and Cowork unified, Cowork's features inside claude.ai chat: chat and Cowork usage by a member who has it turned on is reported under this value instead of `chat` or `cowork`. It is accepted as a filter only on deployments that offer Chat and Cowork unified. Some unattributed usage is reported as "other".
6449
6450 - `rbac_group_id: string or null`
6451
6452 RBAC group (team) the usage is attributed to, in the public tagged `rbac_group_...` spelling — the same spelling the activity resources use for this key, so the same team has one id across resources and it round-trips as an `rbac_group_ids[]` filter value. Populated only when `rbac_group_id` is in `group_by[]`. Any-membership semantics: a user in several groups contributes their full usage to each of those groups' rows, so the named-group rows overlap and their sum can exceed the org total. A null value is the single unassigned row: users in no group on that (UTC) day. For the true org total, run the same query without `group_by[]`.
6453
6454 - `service_tier: BetaAnalyticsServiceTier or null`
6455
6456 Service tier the usage was served at. Populated only when `service_tier` is in `group_by[]`; null for usage with no service tier (for example, code execution) and for Claude Enterprise usage.
6457
6458 - `"batch"`
6459
6460 - `"flex"`
6461
6462 - `"flex_discount"`
6463
6464 - `"priority"`
6465
6466 - `"priority_on_demand"`
6467
6468 - `"standard"`
6469
6470 - `session_id: string or null`
6471
6472 Claude Managed Agents session that incurred the usage. Populated only when `session_id` is in `group_by[]`; null for usage outside a managed session.
6473
6474 - `slack_channel_id: string or null`
6475
6476 Slack channel the usage originated from. Populated only when `slack_channel_id` is in `group_by[]`; null for usage outside Slack (and for rows recorded before channel attribution was enabled).
6477
6478 - `speed: BetaAnalyticsSpeed or null`
6479
6480 Inference speed mode of the usage or cost: `fast` or `standard`. Null unless `speed` is in `group_by[]`.
6481
6482 - `"fast"`
6483
6484 - `"standard"`
6485
6486 - `token_type: BetaAnalyticsTokenType or null`
6487
6488 Token type when `cost_type` is `tokens`; null otherwise.
6489
6490 - `"cache_creation.ephemeral_1h_input_tokens"`
6491
6492 - `"cache_creation.ephemeral_5m_input_tokens"`
6493
6494 - `"cache_read_input_tokens"`
6495
6496 - `"output_tokens"`
6497
6498 - `"uncached_input_tokens"`
6499
6500 - `user_profile_id: string or null`
6501
6502 User profile the usage was attributed to, as a tagged `uprof_` ID. Populated only when `user_profile_id` is in `group_by[]`; null for usage that named no profile and for Claude Enterprise usage.
6503
6504 - `workspace_id: string or null`
6505
6506 Workspace the usage occurred in, as a tagged workspace ID, including the organization's default workspace. Populated only when `workspace_id` is in `group_by[]`; null for Claude Enterprise usage.
6507
6508 - `starting_at: string`
6509
6510 Start of the period this row covers (inclusive), as an RFC 3339 UTC timestamp: the start of the row's time bucket when a time-bucket width is set, otherwise the requested `starting_at` rounded down to the hour.
6511
6512 format: date-time
6513
6514- `data_refreshed_at: string or null`
6515
6516 RFC 3339 timestamp of the export this response was served from. Null when no export yet covers any part of the requested range, in which case `data` is empty. Data beyond this watermark is incomplete; for stable results, set `ending_at` to this value or earlier. Data is typically refreshed every 4 hours. Values can be revised as late events arrive and reconciliation runs, until about 7 days after the end of the calendar month the usage falls in; for example, values for October 1 can change until about November 7.
6517
6518 format: date-time
6519
6520- `has_more: boolean`
6521
6522 Whether another page is available. When true, pass `next_page` as the `page` parameter to fetch it.
6523
6524- `next_page: string or null`
6525
6526 Opaque cursor for the next page, or null when `has_more` is false. Pass it as the `page` parameter, keeping the other parameters unchanged. A cursor can expire after the underlying data refreshes; the request then returns HTTP 410 and pagination must restart from the first page.
6527
6528#### Example
6529
6530```bash
6531curl https://api.anthropic.com/v1/organizations/analytics/cost \
6532 -H 'anthropic-version: 2026-10-21' \
6533 -H 'anthropic-beta: analytics-usage-cost-2026-08-24' \
6534 -H "Authorization: Bearer $ANTHROPIC_API_KEY"
6535```
6536
6537##### Response (200)
6538
6539```json
6540{
6541 "data": [
6542 {
6543 "cost": {
6544 "amount": "41280.000000",
6545 "currency": "USD",
6546 "list_amount": "51600.000000",
6547 "requests": 128
6548 },
6549 "ending_at": "2026-10-01T00:00:00Z",
6550 "group": {
6551 "actor": {
6552 "deleted": false,
6553 "email_address": "[email protected]",
6554 "name": "Jane Doe",
6555 "type": "user_actor",
6556 "user_id": "user_01WCz1FkmYMm4gnmykNKUu3Q"
6557 },
6558 "actor_type": "user_actor",
6559 "agent_id": "agent_01VHd3EAGJ6PLkP9LM7DDu3f",
6560 "api_key_id": "apikey_01Rj2N8SVvo6BePZj99NhmiT",
6561 "claude_tag_category": "dm",
6562 "claude_tag_user_id": "U0123ABCDEF",
6563 "context_window": "0-200k",
6564 "cost_type": "tokens",
6565 "deployment_id": "depl_01JFC6ihzZHtAuyHsaENdJhY",
6566 "environment_id": "env_017oTjuGedHtjhJauVC5xGJD",
6567 "inference_geo": "global",
6568 "model": "claude-opus-5-5",
6569 "product": "chat",
6570 "rbac_group_id": "rbac_group_012rppKaSVsmTo6NqRDXQXNF",
6571 "service_tier": "standard",
6572 "session_id": "sesn_0187kPDyNCwibNNvfaPEApCJ",
6573 "slack_channel_id": "C0123ABCDEF",
6574 "speed": "fast",
6575 "token_type": "cache_creation.ephemeral_1h_input_tokens",
6576 "user_profile_id": "uprof_01M33NeYUQK2WV9PpYcsPHLi",
6577 "workspace_id": "wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ"
6578 },
6579 "starting_at": "2026-09-01T00:00:00Z"
6580 }
6581 ],
6582 "data_refreshed_at": "2019-12-27T18:11:19.117Z",
6583 "has_more": true,
6584 "next_page": "next_page"
6585}
6586```
6587
46606588## Analytics › Usage Report
46616589
46626590### Get Token Usage Over Time
46636591
46646592**GET** `/v1/organizations/analytics/usage_report`
46656593
4666Get token usage over time across a date range.
4667
4668Returns token usage bucketed by minute, hour, or day, optionally broken
4669down by product, model, context window, inference region, or speed.
4670Available to organizations on a Claude Enterprise plan. Requires an API
4671key with the `read:analytics` scope.
6594[Legacy] Get token usage over time across a date range.
6595
6596Returns token usage bucketed by minute, hour, or day, optionally broken down by one or more `group_by[]` dimensions, such as product or model. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope.
6597
6598This endpoint is one of the legacy Claude Enterprise usage and cost reports. For new integrations, use [`GET /v1/organizations/analytics/usage`](https://platform.claude.com/docs/en/api/beta/organization/analytics/usage/list?sdk_languages=http) in the Usage and Cost Analytics API instead. To move an existing integration, see [Migrate from the Claude Enterprise usage and cost reports](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api?sdk_languages=http#migrate-from-enterprise-analytics-reports).
46726599
46736600#### Query parameters
46746601
from line 6958
50316958
50326959**GET** `/v1/organizations/analytics/user_usage_report`
50336960
5034Get per-user token usage across a date range.
5035
5036Returns one row per user, ranked by the chosen token metric. Use this to
5037see which users consume the most tokens. Only usage attributable to a
5038seat user is included; for organization-wide totals including direct
5039API-key and automation traffic, use the bucketed
5040`/v1/organizations/analytics/usage_report` endpoint. Available to
5041organizations on a Claude Enterprise plan. Requires an API key with the
5042`read:analytics` scope.
6961[Legacy] Get per-user token usage across a date range.
6962
6963Returns usage per user, ranked by the chosen token metric; `group_by[]` or `bucket_width` splits a user across several rows. Use this to see which users consume the most tokens. Only usage attributed to a user account is included; usage with no user attributed to it, such as requests attributed only to an API key, is left out. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope.
6964
6965This endpoint is one of the legacy Claude Enterprise usage and cost reports. For new integrations, use [`GET /v1/organizations/analytics/usage`](https://platform.claude.com/docs/en/api/beta/organization/analytics/usage/list?sdk_languages=http) in the Usage and Cost Analytics API instead. To move an existing integration, see [Migrate from the Claude Enterprise usage and cost reports](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api?sdk_languages=http#migrate-from-enterprise-analytics-reports).
50436966
50446967#### Query parameters
50456968
from line 7381
54587381
54597382**GET** `/v1/organizations/analytics/cost_report`
54607383
5461Get cost in USD over time across a date range.
5462
5463Returns cost bucketed by minute, hour, or day, optionally broken down by
5464product, model, context window, inference region, speed, cost type, or
5465token type. Available to organizations on a Claude Enterprise plan.
5466Requires an API key with the `read:analytics` scope.
7384[Legacy] Get cost in USD over time across a date range.
7385
7386Returns cost bucketed by minute, hour, or day, optionally broken down by one or more `group_by[]` dimensions, such as model or cost type. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope.
7387
7388This endpoint is one of the legacy Claude Enterprise usage and cost reports. For new integrations, use [`GET /v1/organizations/analytics/cost`](https://platform.claude.com/docs/en/api/beta/organization/analytics/cost/list?sdk_languages=http) in the Usage and Cost Analytics API instead. To move an existing integration, see [Migrate from the Claude Enterprise usage and cost reports](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api?sdk_languages=http#migrate-from-enterprise-analytics-reports).
54677389
54687390#### Query parameters
54697391
from line 7749
58277749
58287750**GET** `/v1/organizations/analytics/user_cost_report`
58297751
5830Get per-user cost in USD across a date range.
5831
5832Returns one row per user, ranked by spend. Use this to see which users
5833account for the most cost. Only cost attributable to a seat user is
5834included; for organization-wide totals including direct API-key and
5835automation traffic, use the bucketed
5836`/v1/organizations/analytics/cost_report` endpoint. Available to
5837organizations on a Claude Enterprise plan. Requires an API key with the
5838`read:analytics` scope.
7752[Legacy] Get per-user cost in USD across a date range.
7753
7754Returns cost per user, ranked by spend; `group_by[]` or `bucket_width` splits a user across several rows. Use this to see which users account for the most cost. Only cost attributed to a user account is included; cost with no user attributed to it, such as requests attributed only to an API key, is left out. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope.
7755
7756This endpoint is one of the legacy Claude Enterprise usage and cost reports. For new integrations, use [`GET /v1/organizations/analytics/cost`](https://platform.claude.com/docs/en/api/beta/organization/analytics/cost/list?sdk_languages=http) in the Usage and Cost Analytics API instead. To move an existing integration, see [Migrate from the Claude Enterprise usage and cost reports](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api?sdk_languages=http#migrate-from-enterprise-analytics-reports).
58397757
58407758#### Query parameters
58417759
58427760
api/beta/organization/analytics/cost New page · 1369 lines, new page
# Cost ## Get Cost By Dimension ### Query parameters ### Headers ### Returns ### Example #### Response (200) ## Domain types ### Beta Analytics Cost Group ### Beta Analytics Cost Group By ### Beta Analytics Cost Item ### Beta Analytics Cost Metrics ### Beta Analytics Cost Order By
A whole new page. There's nothing to diff it against, so here is what it says.
--- title: Cost url: https://platform.claude.com/docs/en/api/beta/organization/analytics/cost --- # Cost ## Get Cost By Dimension **GET** `/v1/organizations/analytics/cost` Get cost in USD across a date range, broken out by dimension. Returns one row per combination of the requested `group_by[]` dimensions (and time bucket, when `time_bucket_width` is set) that has cost in the range, ranked by spend or ordered by time bucket; every combination is returned across pages. With no `group_by[]` and no `time_bucket_width`, a single row aggregates the whole range. Includes all cost, whether or not it is attributable to a seat user. Requires an API key with the `read:analytics` scope, or an Admin API key. ### Query parameters - `starting_at: string` Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `actor_ids: optional array of string` Filter to usage attributed to specific identities, by tagged ID: a `user_...`, `svac_...` (service account), or `apikey_...` ID. An `apikey_` entry matches only usage attributed to the key itself, not usage on that key attributed to a user or service account (use `api_key_ids[]` for every request a key authenticated). Federated identities have no tagged ID; select them with `actor_types[]`. Use `group_by[]=actor` to break out per-identity values. maxItems: 100 - `actor_types: optional array of BetaAnalyticsActorType` Filter to usage attributed to specific kinds of identity. Use `group_by[]=actor_type` to break out per-kind values. maxItems: 100 - `"api_actor"` - `"federated_actor"` - `"service_account_actor"` - `"user_actor"` - `agent_ids: optional array of string` Filter to usage incurred by sessions of specific Claude Managed Agents agents. Use `group_by[]=agent_id` to break out per-agent values. Claude Developer Platform organizations only. maxItems: 100 - `api_key_ids: optional array of string` Filter to usage authenticated by specific API keys, by tagged API key ID (`apikey_...`), whichever identity the usage is attributed to. Include an empty entry (`api_key_ids[]=`) to also match usage that no API key authenticated. Use `group_by[]=api_key_id` to break out per-key values; usage without a key has a null `api_key_id`. Claude Developer Platform organizations only. maxItems: 100 - `claude_tag_categories: optional array of BetaAnalyticsClaudeTagCategory` Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude_tag`, so combining this filter with `products[]=claude_tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: optional array of string` Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: optional array of BetaAnalyticsContextWindow` Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `deployment_ids: optional array of string` Filter to usage incurred by Claude Managed Agents sessions that specific deployments started. Use `group_by[]=deployment_id` to break out per-deployment values. Claude Developer Platform organizations only. maxItems: 100 - `ending_at: optional string` End of range, exclusive. Required when `time_bucket_width` is set. Without `time_bucket_width`, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `environment_ids: optional array of string` Filter to usage incurred by Claude Managed Agents sessions that ran in specific environments. Use `group_by[]=environment_id` to break out per-environment values. Claude Developer Platform organizations only. maxItems: 100 - `exclude_deleted_users: optional boolean` If true, omit rows whose `actor` is a `user_actor` with `deleted: true`. Requires `group_by[]=actor`. Rows for other actor types, and rows whose `actor` is null, are always kept. A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual. default: false - `group_by: optional array of BetaAnalyticsCostGroupBy` Dimensions to break cost out by (at most 5, not counting `cost_type` and `token_type`): one row per combination of their values with cost in the range (and per time bucket, when `time_bucket_width` is set), every combination returned across pages rather than a capped top set. `cost_type` and `token_type` do not count toward `limit`: `cost_type` returns one row per cost component (tokens, web search, code execution, and `session_usage`, Claude Managed Agents session time); `token_type` returns one row per token type, each with `cost_type: "tokens"`; combining both returns the per-token-type rows plus the web-search, code-execution and session-usage rows. When omitted, a single row aggregates the whole range. maxItems: 100 - `"actor"` - `"actor_type"` - `"agent_id"` - `"api_key_id"` - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"cost_type"` - `"deployment_id"` - `"environment_id"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"service_tier"` - `"session_id"` - `"slack_channel_id"` - `"speed"` - `"token_type"` - `"user_profile_id"` - `"workspace_id"` - `inference_geos: optional array of BetaAnalyticsInferenceGeoFilter` Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: optional number` Number of rows per page (1-1000, default 20). `cost_type`/`token_type` fan-out rows (cost endpoint only) do not count toward this limit, so `data` can exceed it. default: 20, minimum: 1, maximum: 1000 - `models: optional array of string` Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `order: optional BetaAnalyticsUsageCostSortOrder` Sort direction of the `order_by` metric, or of the time buckets when `order_by` is `time` and `time_bucket_width` is set. Defaults to `desc`. - `"asc"` - `"desc"` - `order_by: optional BetaAnalyticsCostOrderBy` Row order. A metric ranks rows by that metric in the `order` direction. `time` orders rows by time bucket in the `order` direction (newest first by default) and, within a bucket, by `amount`, highest first. `time` takes effect only with `time_bucket_width`; without it, `time` is the same as `amount`. Defaults to `amount`. - `"amount"` - `"list_amount"` - `"time"` - `page: optional string` Opaque cursor from a previous response's `next_page` field. - `products: optional array of BetaAnalyticsUsageCostProductFilter` Product surfaces to include. Defaults to all products. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude_code"` - `"claude_console"` - `"claude_design"` - `"claude_in_chrome"` - `"claude_tag"` - `"cowork"` - `"managed_agents_api"` - `"message_batches_api"` - `"messages_api"` - `"office_agent"` - `rbac_group_ids: optional array of string` Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `service_tiers: optional array of BetaAnalyticsServiceTier` Filter to specific service tiers. Use `group_by[]=service_tier` to break out per-tier values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization. maxItems: 100 - `"batch"` - `"flex"` - `"flex_discount"` - `"priority"` - `"priority_on_demand"` - `"standard"` - `session_ids: optional array of string` Filter to usage incurred by specific Claude Managed Agents sessions, by tagged session ID (`sesn_...`). Use `group_by[]=session_id` to break out per-session values. Claude Developer Platform organizations only. maxItems: 100 - `slack_channel_ids: optional array of string` Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: optional array of BetaAnalyticsSpeed` Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `time_bucket_width: optional BetaAnalyticsTimeBucketWidth` Time-bucket granularity. When set, rows are returned per time bucket (one per bucket and dimension combination with usage) and each row's `starting_at` and `ending_at` are that bucket's bounds; the time bucket counts toward `limit`. `ending_at` is required when `time_bucket_width` is set, and with `time_bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the requested range with `starting_at` and `ending_at` each rounded down to the hour. - `"1d"` - `"1h"` - `"1m"` - `user_profile_ids: optional array of string` Filter to usage attributed to specific user profiles, by tagged user profile ID (`uprof_...`). Use `group_by[]=user_profile_id` to break out per-profile values. Claude Developer Platform organizations only.
Cut at 300 lines. The page has the rest.
api/beta/organization/analytics/cost/list New page · 776 lines, new page
# Get Cost By Dimension ## Query parameters ## Headers ## Returns ## Example ### Response (200)
A whole new page. There's nothing to diff it against, so here is what it says.
--- title: Get Cost By Dimension url: https://platform.claude.com/docs/en/api/beta/organization/analytics/cost/list --- # Get Cost By Dimension **GET** `/v1/organizations/analytics/cost` Get cost in USD across a date range, broken out by dimension. Returns one row per combination of the requested `group_by[]` dimensions (and time bucket, when `time_bucket_width` is set) that has cost in the range, ranked by spend or ordered by time bucket; every combination is returned across pages. With no `group_by[]` and no `time_bucket_width`, a single row aggregates the whole range. Includes all cost, whether or not it is attributable to a seat user. Requires an API key with the `read:analytics` scope, or an Admin API key. ## Query parameters - `starting_at: string` Start of range, inclusive. RFC 3339 tz-aware. Must be within the last 365 days and no earlier than 2026-01-01T00:00:00Z. format: date-time - `actor_ids: optional array of string` Filter to usage attributed to specific identities, by tagged ID: a `user_...`, `svac_...` (service account), or `apikey_...` ID. An `apikey_` entry matches only usage attributed to the key itself, not usage on that key attributed to a user or service account (use `api_key_ids[]` for every request a key authenticated). Federated identities have no tagged ID; select them with `actor_types[]`. Use `group_by[]=actor` to break out per-identity values. maxItems: 100 - `actor_types: optional array of BetaAnalyticsActorType` Filter to usage attributed to specific kinds of identity. Use `group_by[]=actor_type` to break out per-kind values. maxItems: 100 - `"api_actor"` - `"federated_actor"` - `"service_account_actor"` - `"user_actor"` - `agent_ids: optional array of string` Filter to usage incurred by sessions of specific Claude Managed Agents agents. Use `group_by[]=agent_id` to break out per-agent values. Claude Developer Platform organizations only. maxItems: 100 - `api_key_ids: optional array of string` Filter to usage authenticated by specific API keys, by tagged API key ID (`apikey_...`), whichever identity the usage is attributed to. Include an empty entry (`api_key_ids[]=`) to also match usage that no API key authenticated. Use `group_by[]=api_key_id` to break out per-key values; usage without a key has a null `api_key_id`. Claude Developer Platform organizations only. maxItems: 100 - `claude_tag_categories: optional array of BetaAnalyticsClaudeTagCategory` Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `claude_tag`, so combining this filter with `products[]=claude_tag` excludes it. Use `group_by[]=claude_tag_category` to break out per-category values. maxItems: 100 - `"dm"` - `"engaged"` - `"monitoring"` - `"proactive"` - `"scheduled"` - `claude_tag_user_ids: optional array of string` Filter to Claude Tag (Claude in Slack) usage attributed to specific Slack users, by Slack user ID (for example `U0123ABCDEF`), not claude.ai user ID. Usage that is not Claude Tag, and Claude Tag usage not attributed to a single user, never matches. Use `group_by[]=claude_tag_user_id` to break out per-user values. maxItems: 100 - `context_windows: optional array of BetaAnalyticsContextWindow` Filter to specific context-window pricing tiers. Use `group_by[]=context_window` to break out per-tier values. maxItems: 100 - `"0-200k"` - `"200k-1M"` - `deployment_ids: optional array of string` Filter to usage incurred by Claude Managed Agents sessions that specific deployments started. Use `group_by[]=deployment_id` to break out per-deployment values. Claude Developer Platform organizations only. maxItems: 100 - `ending_at: optional string` End of range, exclusive. Required when `time_bucket_width` is set. Without `time_bucket_width`, defaults to the earlier of now and `starting_at` + 31 days. The range may span at most 31 days. format: date-time - `environment_ids: optional array of string` Filter to usage incurred by Claude Managed Agents sessions that ran in specific environments. Use `group_by[]=environment_id` to break out per-environment values. Claude Developer Platform organizations only. maxItems: 100 - `exclude_deleted_users: optional boolean` If true, omit rows whose `actor` is a `user_actor` with `deleted: true`. Requires `group_by[]=actor`. Rows for other actor types, and rows whose `actor` is null, are always kept. A page may contain fewer than `limit` rows; use `has_more` and `next_page` to paginate as usual. default: false - `group_by: optional array of BetaAnalyticsCostGroupBy` Dimensions to break cost out by (at most 5, not counting `cost_type` and `token_type`): one row per combination of their values with cost in the range (and per time bucket, when `time_bucket_width` is set), every combination returned across pages rather than a capped top set. `cost_type` and `token_type` do not count toward `limit`: `cost_type` returns one row per cost component (tokens, web search, code execution, and `session_usage`, Claude Managed Agents session time); `token_type` returns one row per token type, each with `cost_type: "tokens"`; combining both returns the per-token-type rows plus the web-search, code-execution and session-usage rows. When omitted, a single row aggregates the whole range. maxItems: 100 - `"actor"` - `"actor_type"` - `"agent_id"` - `"api_key_id"` - `"claude_tag_category"` - `"claude_tag_user_id"` - `"context_window"` - `"cost_type"` - `"deployment_id"` - `"environment_id"` - `"inference_geo"` - `"model"` - `"product"` - `"rbac_group_id"` - `"service_tier"` - `"session_id"` - `"slack_channel_id"` - `"speed"` - `"token_type"` - `"user_profile_id"` - `"workspace_id"` - `inference_geos: optional array of BetaAnalyticsInferenceGeoFilter` Filter to specific inference regions. `not_available` matches rows where the region is unset. Use `group_by[]=inference_geo` to break out per-region values. maxItems: 100 - `"global"` - `"not_available"` - `"us"` - `limit: optional number` Number of rows per page (1-1000, default 20). `cost_type`/`token_type` fan-out rows (cost endpoint only) do not count toward this limit, so `data` can exceed it. default: 20, minimum: 1, maximum: 1000 - `models: optional array of string` Models to include. Defaults to all models. Use `group_by[]=model` to break out per-model values. maxItems: 100 - `order: optional BetaAnalyticsUsageCostSortOrder` Sort direction of the `order_by` metric, or of the time buckets when `order_by` is `time` and `time_bucket_width` is set. Defaults to `desc`. - `"asc"` - `"desc"` - `order_by: optional BetaAnalyticsCostOrderBy` Row order. A metric ranks rows by that metric in the `order` direction. `time` orders rows by time bucket in the `order` direction (newest first by default) and, within a bucket, by `amount`, highest first. `time` takes effect only with `time_bucket_width`; without it, `time` is the same as `amount`. Defaults to `amount`. - `"amount"` - `"list_amount"` - `"time"` - `page: optional string` Opaque cursor from a previous response's `next_page` field. - `products: optional array of BetaAnalyticsUsageCostProductFilter` Product surfaces to include. Defaults to all products. maxItems: 100 - `"chat"` - `"chat_cowork_unified"` - `"claude_code"` - `"claude_console"` - `"claude_design"` - `"claude_in_chrome"` - `"claude_tag"` - `"cowork"` - `"managed_agents_api"` - `"message_batches_api"` - `"messages_api"` - `"office_agent"` - `rbac_group_ids: optional array of string` Filter to usage attributed to specific RBAC groups. Accepts tagged RBAC group IDs (`rbac_group_...`) or bare group UUIDs. A row matches when the user belonged to any of the listed groups on the (UTC) day the usage occurred; usage with no group attribution never matches. maxItems: 100 - `service_tiers: optional array of BetaAnalyticsServiceTier` Filter to specific service tiers. Use `group_by[]=service_tier` to break out per-tier values. Claude Developer Platform organizations only; matches nothing for a Claude Enterprise organization. maxItems: 100 - `"batch"` - `"flex"` - `"flex_discount"` - `"priority"` - `"priority_on_demand"` - `"standard"` - `session_ids: optional array of string` Filter to usage incurred by specific Claude Managed Agents sessions, by tagged session ID (`sesn_...`). Use `group_by[]=session_id` to break out per-session values. Claude Developer Platform organizations only. maxItems: 100 - `slack_channel_ids: optional array of string` Filter to usage originating from specific Slack channels. Use `group_by[]=slack_channel_id` to break out per-channel values. maxItems: 100 - `speeds: optional array of BetaAnalyticsSpeed` Filter to fast or standard inference mode. Use `group_by[]=speed` to break out per-mode values. maxItems: 100 - `"fast"` - `"standard"` - `time_bucket_width: optional BetaAnalyticsTimeBucketWidth` Time-bucket granularity. When set, rows are returned per time bucket (one per bucket and dimension combination with usage) and each row's `starting_at` and `ending_at` are that bucket's bounds; the time bucket counts toward `limit`. `ending_at` is required when `time_bucket_width` is set, and with `time_bucket_width="1m"` the range may span at most 24 hours. When omitted, each row aggregates the requested range with `starting_at` and `ending_at` each rounded down to the hour. - `"1d"` - `"1h"` - `"1m"` - `user_profile_ids: optional array of string` Filter to usage attributed to specific user profiles, by tagged user profile ID (`uprof_...`). Use `group_by[]=user_profile_id` to break out per-profile values. Claude Developer Platform organizations only. maxItems: 100
Cut at 300 lines. The page has the rest.
api/beta/organization/analytics/cost_report Changed · +5 / -6 lines
from line 9
99
1010**GET** `/v1/organizations/analytics/cost_report`
1111
12Get cost in USD over time across a date range.
12[Legacy] Get cost in USD over time across a date range.
1313
14Returns cost bucketed by minute, hour, or day, optionally broken down by
15product, model, context window, inference region, speed, cost type, or
16token type. Available to organizations on a Claude Enterprise plan.
17Requires an API key with the `read:analytics` scope.
14Returns cost bucketed by minute, hour, or day, optionally broken down by one or more `group_by[]` dimensions, such as model or cost type. Available to organizations on a Claude Enterprise plan. Requires an API key with the `read:analytics` scope.
15
16This endpoint is one of the legacy Claude Enterprise usage and cost reports. For new integrations, use [`GET /v1/organizations/analytics/cost`](https://platform.claude.com/docs/en/api/beta/organization/analytics/cost/list?sdk_languages=http) in the Usage and Cost Analytics API instead. To move an existing integration, see [Migrate from the Claude Enterprise usage and cost reports](https://platform.claude.com/docs/en/manage-claude/usage-cost-analytics-api?sdk_languages=http#migrate-from-enterprise-analytics-reports).
1817
1918### Query parameters
2019