Follow Discord
Sweep 28 Sep 2026 · 18:16Z Build v2.1.284 505 read Stable v2.1.277 Latest v2.1.284 Next v2.1.284 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One capture · api

One read of Claude Developer Platformapi-20260929T013708Z

77 pages moved out of 639 read.

Pages moved 77 significant first
Pages read 639 in this capture
Captured 01:37 UTC
Corpus hash 2ca3d5042784 corpus-hash

What this read moved

1-25 of 77, page 1 of 4

This capture is too large to show at once. Changes 1-25 of 77 are below, significant first; the rest are on the following screens.

agents-and-tools/mcp-connector Changed · +4 / -4 lines

from line 1236
12361236 <Tabs>
12371237 <Tab title="Gradle">
12381238 ```kotlin
1239 implementation("com.anthropic:anthropic-java:2.65.0")
1240 implementation("com.anthropic:anthropic-java-mcp:2.65.0")
1239 implementation("com.anthropic:anthropic-java:2.66.0")
1240 implementation("com.anthropic:anthropic-java-mcp:2.66.0")
12411241 ```
12421242 </Tab>
12431243 
from line 1246
12461246 <dependency>
12471247 <groupId>com.anthropic</groupId>
12481248 <artifactId>anthropic-java</artifactId>
1249 <version>2.65.0</version>
1249 <version>2.66.0</version>
12501250 </dependency>
12511251 <dependency>
12521252 <groupId>com.anthropic</groupId>
12531253 <artifactId>anthropic-java-mcp</artifactId>
1254 <version>2.65.0</version>
1254 <version>2.66.0</version>
12551255 </dependency>
12561256 ```
12571257 </Tab>

api/beta Changed · +4368 / -4002 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 4301
43014301 
43024302 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
43034303 
4304 - `string`
4304 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
43054305 
4306 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
4307 
43084306 The model that will complete your prompt.
43094307 
43104308 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
43114309 
4310 - `"claude-sonnet-5-5"`
4311 
4312 Efficient model for coding and agents
4313 
43124314 - `"claude-fable-5-1"`
43134315 
43144316 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 4325
43234325 
43244326 - `"claude-sonnet-5"`
43254327 
4326 High-performance model for coding and agents
4328 Efficient model for coding and agents
43274329 
43284330 - `"claude-fable-5"`
43294331 
from line 4385
43834385 
43844386 New class of intelligence, strongest in coding and cybersecurity
43854387 
4388 - `string`
4389 
43864390 - `name: "advisor"`
43874391 
43884392 Name of the tool.
from line 5021
50175021 
50185022 - `"fast"`
50195023 
5020 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null`
5024 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
50215025 
50225026 - `BetaThinkingConfigEnabled object`
50235027 
from line 5063
50595063 
50605064 - `type: "disabled"`
50615065 
5066 - `BetaThinkingConfigBetweenTools object`
5067 
5068 - `type: "between_tools"`
5069 
50625070 - `BetaThinkingConfigAdaptive object`
50635071 
50645072 - `type: "adaptive"`
from line 5155
51475155 
51485156- `stream: optional boolean`
51495157 
5150 Whether to incrementally stream the response using server-sent events.
5158 Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
51515159 
5152 See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
5160 In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming#streaming-with-sdks) for an example in each language.
51535161 
51545162- `system: optional string or array of BetaTextBlockParam`
51555163 
from line 5193
51855193 
51865194 - `BetaThinkingConfigDisabled object`
51875195 
5196 - `BetaThinkingConfigBetweenTools object`
5197 
51885198 - `BetaThinkingConfigAdaptive object`
51895199 
51905200- `tool_choice: optional BetaToolChoice`
from line 7763
77537763 
77547764 minimum: 1
77557765 
7756 - `strict: optional boolean`
7757 
7758 When true, guarantees schema validation on tool names and inputs
7759 
7760 - `url_sources: optional BetaWebFetchURLSources or null`
7761 
7762 Which sources contribute to the set of URLs the tool may fetch. Omitted means every source.
7763 
7764 - `client_tool_results: optional BetaWebFetchURLSourceAll or BetaWebFetchURLSourceNone or BetaWebFetchURLSourceOnly or BetaWebFetchURLSourceExcept`
7765 
7766 Which client tools' results contribute fetchable URLs: "all"
7766 - `strict: optional

api/beta/agents Changed · +3562 / -3510 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 Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control
131131 
132 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
132 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
133133 
134134 The model that will power your agent.
135135 
136136 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
137137 
138 - `string`
138 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
139139 
140 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
141 
142140 The model that will power your agent.
143141 
144142 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
145143 
144 - `"claude-sonnet-5-5"`
145 
146 Efficient model for coding and agents
147 
146148 - `"claude-opus-5-5"`
147149 
148150 Powerful intelligence for coding, knowledge work, and long-running agents
from line 155
153155 
154156 - `"claude-sonnet-5"`
155157 
156 High-performance model for coding and agents
158 Efficient model for coding and agents
157159 
158160 - `"claude-fable-5"`
159161 
from line 205
203205 
204206 High-performance model for agents and coding
205207 
208 - `string`
209 
206210 - `BetaManagedAgentsModelConfigParams object`
207211 
208212 An object that defines additional configuration control over model use
from line 889
885889 
886890 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
887891 
888 - `string`
892 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
889893 
890 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
891 
892894 The model that will power your agent.
893895 
894896 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
895897 
898 - `"claude-sonnet-5-5"`
899 
900 Efficient model for coding and agents
901 
896902 - `"claude-opus-5-5"`
897903 
898904 Powerful intelligence for coding, knowledge work, and long-running agents
from line 909
903909 
904910 - `"claude-sonnet-5"`
905911 
906 High-performance model for coding and agents
912 Efficient model for coding and agents
907913 
908914 - `"claude-fable-5"`
909915 
from line 959
953959 
954960 High-performance model for agents and coding
955961 
962 - `string`
963 
956964 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
957965 
958966 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 1733
17251733 
17261734 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
17271735 
1728 - `string`
1736 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
17291737 
1730 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
1731 
17321738 The model that will power your agent.
17331739 
17341740 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
17351741 
1742 - `"claude-sonnet-5-5"`
1743 
1744 Efficient model for coding and agents
1745 
17361746 - `"claude-opus-5-5"`
17371747 
17381748 Powerful intelligence for coding, knowledge work, and long-running agents
from line 1753
17431753 
17441754 - `"claude-sonnet-5"`
17451755 
1746 High-performance model for coding and agents
1756 Efficient model for coding and agents
17471757 
17481758 - `"claude-fable-5"`
17491759 
from line 1803
17931803 
17941804 High-performance model for agents and coding
17951805 
1806 - `string`
1807 
17961808 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
17971809 
17981810 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 2548
25362548 
25372549 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25382550 
2539 - `string`
2551 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
25402552 
2541 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
2542 
25432553 The model that will power your agent.
25442554 
25452555 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25462556 
2557 - `"claude-sonnet-5-5"`
2558 
2559 Efficient model for coding and agents
2560 
25472561 - `"claude-opus-5-5"`
25482562 
25492563 Powerful intelligence for coding, knowledge work, and long-running agents
from line 2568
25542568 
25552569 - `"claude-sonnet-5"`
25562570 
2557 High-performance model for coding and agents
2571 Efficient model for coding and agents
25582572 
25592573 - `"claude-fable-5"`
25602574 
from line 2618
26042618 
26052619 High-performance model for agents and coding
26062620 
2621 - `string`
2622 
26072623 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
26082624 
26092625 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 3336
33203336 
33213337 Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control. Omit to preserve. Cannot be cleared.
33223338 
3323 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
3339 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
33243340 
33253341 The model that will power your agent.
33263342 
33273343 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
33283344 
3329 - `string`
3345 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
33303346 
3331 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
3332 
33333347 The model that will power your agent.
33343348 
33353349 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
33363350 
3351 - `"claude-sonnet-5-5"`
3352 
3353 Efficient model for coding and agents
3354 
33373355 - `"claude-opus-5-5"`
33383356 
33393357 Powerful intelligence for coding, knowledge work, and long-running agents
from line 3362
33443362 
33453363 - `"claude-sonnet-5"`
33463364 
3347 High-performance model for coding and agents
3365 Efficient model for coding and agents
33483366 
33493367 - `"claude-fable-5"`
33503368 
from line 3412
33943412 
33953413 High-performance model for agents and coding
33963414 
3415 - `string`
3416 
33973417 - `BetaManagedAgentsModelConfigParams object`
33983418 
33993419 An object that defines additional configuration control over model use
from line 4074
40544074 
40554075 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
40564076 
4057 - `string`
4077 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
40584078 
4059 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
4060 
40614079 The model that will power your agent.
40624080 
40634081 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
40644082 
4083 - `"claude-sonnet-5-5"`
4084 
4085 Efficient model for coding and agents
4086 
40654087 - `"claude-opus-5-5"`
40664088 
40674089 Powerful intelligence for coding, knowledge work, and long-running agents
from line 4094
40724094 
40734095 - `"claude-sonnet-5"`
40744096 
4075 High-performance model for coding and agents
4097 Efficient model for coding and agents
40764098 
40774099 - `"claude-fable-5"`
40784100 
from line 4144
41224144 
41234145 High-performance model for agents and coding
41244146 
4147 - `string`
4148 
41254149 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
41264150 
41274151 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 4887
48634887 
48644888 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
48654889 
4866 - `string`
4890 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
48674891 
4868 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
4869 
48704892 The model that will power your agent.
48714893 
48724894 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
48734895 
4896 - `"claude-sonnet-5-5"`
4897 
4898 Efficient model for coding and agents
4899 
48744900 - `"claude-opus-5-5"`
48754901 
48764902 Powerful intelligence for coding, knowledge work, and long-running agents
from line 4907
48814907 
48824908 - `"claude-sonnet-5"`
48834909 
4884 High-performance model for coding and agents
4910 Efficient model for coding and agents
48854911 
48864912 - `"claude-fable-5"`
48874913 
from line 4957
49314957 
49324958 High-performance model for agents and coding
49334959 
4960 - `string`
4961 
49344962 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
49354963 
49364964 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 5576
55485576 
55495577 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
55505578 
5551 - `string`
5579 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
55525580 
5553 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
5554 
55555581 The model that will power your agent.
55565582 
55575583 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
55585584 
5585 - `"claude-sonnet-5-5"`
5586 
5587 Efficient model for coding and agents
5588 
55595589 - `"claude-opus-5-5"`
55605590 
55615591 Powerful intelligence for coding, knowledge work, and long-running agents
from line 5596
55665596 
55675597 - `"claude-sonnet-5"`
55685598 
5569 High-performance model for coding and agents
5599 Efficient model for coding and agents
55705600 
55715601 - `"claude-fable-5"`
55725602 
from line 5646
56165646 
56175647 High-performance model for agents and coding
56185648 
5649 - `string`
5650 
56195651 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
56205652 
56215653 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 8234
82028234 
82038235 - `type: "auto"`
82048236 
8205 - `default_config: optional BetaManagedAgentsMCPToolsetDefaultConfigParams or null`
8206 
8207 Default configuration for all tools from this server.
8208 
8209 - `enabled: optional boolean or null`
8210 
8211 Whether tools are enabled by default. Defaults to true if not specified.
8212 
8213 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
8214 
8215 Default permission policy for tools from this server.
8216 
8217 - `BetaManagedAgentsAlwaysAllowPolicy object`
8218 
8219 Tool calls are automatically approved without user confirmation.
8220 
8221 - `BetaManagedAgentsAlwaysAskPolicy
8237 - `default_config: optional Beta

api/beta/agents/archive Changed · +70 / -66 lines

from line 171
171171 
172172 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
173173 
174 - `string`
174 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
175175 
176 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
177 
178176 The model that will power your agent.
179177 
180178 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
181179 
180 - `"claude-sonnet-5-5"`
181 
182 Efficient model for coding and agents
183 
182184 - `"claude-opus-5-5"`
183185 
184186 Powerful intelligence for coding, knowledge work, and long-running agents
from line 191
189191 
190192 - `"claude-sonnet-5"`
191193 
192 High-performance model for coding and agents
194 Efficient model for coding and agents
193195 
194196 - `"claude-fable-5"`
195197 
from line 240
238240 - `"claude-sonnet-4-5-20250929"`
239241 
240242 High-performance model for agents and coding
243 
244 - `string`
241245 
242246 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
243247 

api/beta/agents/create Changed · +810 / -802 lines

from line 127
127127 
128128 Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control
129129 
130 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
130 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
131131 
132132 The model that will power your agent.
133133 
134134 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
135135 
136 - `string`
136 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
137137 
138 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
139 
140138 The model that will power your agent.
141139 
142140 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
143141 
142 - `"claude-sonnet-5-5"`
143 
144 Efficient model for coding and agents
145 
144146 - `"claude-opus-5-5"`
145147 
146148 Powerful intelligence for coding, knowledge work, and long-running agents
from line 153
151153 
152154 - `"claude-sonnet-5"`
153155 
154 High-performance model for coding and agents
156 Efficient model for coding and agents
155157 
156158 - `"claude-fable-5"`
157159 
from line 203
201203 
202204 High-performance model for agents and coding
203205 
206 - `string`
207 
204208 - `BetaManagedAgentsModelConfigParams object`
205209 
206210 An object that defines additional configuration control over model use
from line 887
883887 
884888 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
885889 
886 - `string`
890 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
887891 
888 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
889 
890892 The model that will power your agent.
891893 
892894 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
893895 
896 - `"claude-sonnet-5-5"`
897 
898 Efficient model for coding and agents
899 
894900 - `"claude-opus-5-5"`
895901 
896902 Powerful intelligence for coding, knowledge work, and long-running agents
from line 907
901907 
902908 - `"claude-sonnet-5"`
903909 
904 High-performance model for coding and agents
910 Efficient model for coding and agents
905911 
906912 - `"claude-fable-5"`
907913 
from line 956
950956 - `"claude-sonnet-4-5-20250929"`
951957 
952958 High-performance model for agents and coding
959 
960 - `string`
953961 
954962 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
955963 

api/beta/agents/list Changed · +70 / -66 lines

from line 193
193193 
194194 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
195195 
196 - `string`
196 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
197197 
198 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
199 
200198 The model that will power your agent.
201199 
202200 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
203201 
202 - `"claude-sonnet-5-5"`
203 
204 Efficient model for coding and agents
205 
204206 - `"claude-opus-5-5"`
205207 
206208 Powerful intelligence for coding, knowledge work, and long-running agents
from line 213
211213 
212214 - `"claude-sonnet-5"`
213215 
214 High-performance model for coding and agents
216 Efficient model for coding and agents
215217 
216218 - `"claude-fable-5"`
217219 
from line 262
260262 - `"claude-sonnet-4-5-20250929"`
261263 
262264 High-performance model for agents and coding
265 
266 - `string`
263267 
264268 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
265269 

api/beta/agents/retrieve Changed · +70 / -66 lines

from line 179
179179 
180180 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
181181 
182 - `string`
182 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
183183 
184 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
185 
186184 The model that will power your agent.
187185 
188186 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
189187 
188 - `"claude-sonnet-5-5"`
189 
190 Efficient model for coding and agents
191 
190192 - `"claude-opus-5-5"`
191193 
192194 Powerful intelligence for coding, knowledge work, and long-running agents
from line 199
197199 
198200 - `"claude-sonnet-5"`
199201 
200 High-performance model for coding and agents
202 Efficient model for coding and agents
201203 
202204 - `"claude-fable-5"`
203205 
from line 248
246248 - `"claude-sonnet-4-5-20250929"`
247249 
248250 High-performance model for agents and coding
251 
252 - `string`
249253 
250254 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
251255 

api/beta/agents/update Changed · +788 / -780 lines

from line 161
161161 
162162 Model identifier. Accepts the [model string](https://platform.claude.com/docs/en/about-claude/models/overview#latest-models-comparison), e.g. `claude-opus-5`, or a `model_config` object for additional configuration control. Omit to preserve. Cannot be cleared.
163163 
164 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
164 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
165165 
166166 The model that will power your agent.
167167 
168168 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
169169 
170 - `string`
170 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
171171 
172 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
173 
174172 The model that will power your agent.
175173 
176174 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
177175 
176 - `"claude-sonnet-5-5"`
177 
178 Efficient model for coding and agents
179 
178180 - `"claude-opus-5-5"`
179181 
180182 Powerful intelligence for coding, knowledge work, and long-running agents
from line 187
185187 
186188 - `"claude-sonnet-5"`
187189 
188 High-performance model for coding and agents
190 Efficient model for coding and agents
189191 
190192 - `"claude-fable-5"`
191193 
from line 237
235237 
236238 High-performance model for agents and coding
237239 
240 - `string`
241 
238242 - `BetaManagedAgentsModelConfigParams object`
239243 
240244 An object that defines additional configuration control over model use
from line 899
895899 
896900 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
897901 
898 - `string`
902 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
899903 
900 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
901 
902904 The model that will power your agent.
903905 
904906 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
905907 
908 - `"claude-sonnet-5-5"`
909 
910 Efficient model for coding and agents
911 
906912 - `"claude-opus-5-5"`
907913 
908914 Powerful intelligence for coding, knowledge work, and long-running agents
from line 919
913919 
914920 - `"claude-sonnet-5"`
915921 
916 High-performance model for coding and agents
922 Efficient model for coding and agents
917923 
918924 - `"claude-fable-5"`
919925 
from line 968
962968 - `"claude-sonnet-4-5-20250929"`
963969 
964970 High-performance model for agents and coding
971 
972 - `string`
965973 
966974 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
967975 

api/beta/agents/versions Changed · +70 / -66 lines

from line 185
185185 
186186 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
187187 
188 - `string`
188 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
189189 
190 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
191 
192190 The model that will power your agent.
193191 
194192 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
195193 
194 - `"claude-sonnet-5-5"`
195 
196 Efficient model for coding and agents
197 
196198 - `"claude-opus-5-5"`
197199 
198200 Powerful intelligence for coding, knowledge work, and long-running agents
from line 205
203205 
204206 - `"claude-sonnet-5"`
205207 
206 High-performance model for coding and agents
208 Efficient model for coding and agents
207209 
208210 - `"claude-fable-5"`
209211 
from line 254
252254 - `"claude-sonnet-4-5-20250929"`
253255 
254256 High-performance model for agents and coding
257 
258 - `string`
255259 
256260 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
257261 

api/beta/agents/versions/list Changed · +70 / -66 lines

from line 183
183183 
184184 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
185185 
186 - `string`
186 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
187187 
188 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
189 
190188 The model that will power your agent.
191189 
192190 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
193191 
192 - `"claude-sonnet-5-5"`
193 
194 Efficient model for coding and agents
195 
194196 - `"claude-opus-5-5"`
195197 
196198 Powerful intelligence for coding, knowledge work, and long-running agents
from line 203
201203 
202204 - `"claude-sonnet-5"`
203205 
204 High-performance model for coding and agents
206 Efficient model for coding and agents
205207 
206208 - `"claude-fable-5"`
207209 
from line 252
250252 - `"claude-sonnet-4-5-20250929"`
251253 
252254 High-performance model for agents and coding
255 
256 - `string`
253257 
254258 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
255259 

api/beta/messages Changed · +2987 / -2817 lines

### Beta Thinking Config Between Tools

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 3104
31043104 
31053105 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31063106 
3107 - `string`
3107 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
31083108 
3109 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
3110 
31113109 The model that will complete your prompt.
31123110 
31133111 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31143112 
3113 - `"claude-sonnet-5-5"`
3114 
3115 Efficient model for coding and agents
3116 
31153117 - `"claude-fable-5-1"`
31163118 
31173119 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 3128
31263128 
31273129 - `"claude-sonnet-5"`
31283130 
3129 High-performance model for coding and agents
3131 Efficient model for coding and agents
31303132 
31313133 - `"claude-fable-5"`
31323134 
from line 3188
31863188 
31873189 New class of intelligence, strongest in coding and cybersecurity
31883190 
3191 - `string`
3192 
31893193 - `name: "advisor"`
31903194 
31913195 Name of the tool.
from line 3824
38203824 
38213825 - `"fast"`
38223826 
3823 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null`
3827 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
38243828 
38253829 - `BetaThinkingConfigEnabled object`
38263830 
from line 3866
38623866 
38633867 - `type: "disabled"`
38643868 
3869 - `BetaThinkingConfigBetweenTools object`
3870 
3871 - `type: "between_tools"`
3872 
38653873 - `BetaThinkingConfigAdaptive object`
38663874 
38673875 - `type: "adaptive"`
from line 3958
39503958 
39513959- `stream: optional boolean`
39523960 
3953 Whether to incrementally stream the response using server-sent events.
3961 Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
39543962 
3955 See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
3963 In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming#streaming-with-sdks) for an example in each language.
39563964 
39573965- `system: optional string or array of BetaTextBlockParam`
39583966 
from line 3996
39883996 
39893997 - `BetaThinkingConfigDisabled object`
39903998 
3999 - `BetaThinkingConfigBetweenTools object`
4000 
39914001 - `BetaThinkingConfigAdaptive object`
39924002 
39934003- `tool_choice: optional BetaToolChoice`
from line 6972
69626972 
69636973 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
69646974 
6965 - `string`
6975 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
69666976 
6967 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
6968 
69696977 The model that will complete your prompt.
69706978 
69716979 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
69726980 
6981 - `"claude-sonnet-5-5"`
6982 
6983 Efficient model for coding and agents
6984 
69736985 - `"claude-fable-5-1"`
69746986 
69756987 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 6996
69846996 
69856997 - `"claude-sonnet-5"`
69866998 
6987 High-performance model for coding and agents
6999 Efficient model for coding and agents
69887000 
69897001 - `"claude-fable-5"`
69907002 
from line 7056
70447056 
70457057 New class of intelligence, strongest in coding and cybersecurity
70467058 
7059 - `string`
7060 
70477061 - `name: "advisor"`
70487062 
70497063 Name of the tool.
from line 7203
71897203 
71907204 - `default_config: optional BetaMCPToolDefaultConfig`
71917205 
7192 Default configuration applied to all tools from this server
7193 
7194 - `defer_loading: optional boolean`
7195 
7196 - `enabled: optional boolean`
7197 
7198 - `tools: optional array of BetaMCPToolParam or null`
7199 
7200 The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response.
7201 
7202 - `input_schema: map[unknown]`
7203 
7204 The tool's input schema as the MCP server lists it, verbatim.
7205 
7206 - `name: s
7206 Default configuration applied to all tools from this serv

api/beta/messages/batches Changed · +430 / -404 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 3124
31243124 
31253125 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31263126 
3127 - `string`
3127 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
31283128 
3129 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
3130 
31313129 The model that will complete your prompt.
31323130 
31333131 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31343132 
3133 - `"claude-sonnet-5-5"`
3134 
3135 Efficient model for coding and agents
3136 
31353137 - `"claude-fable-5-1"`
31363138 
31373139 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 3148
31463148 
31473149 - `"claude-sonnet-5"`
31483150 
3149 High-performance model for coding and agents
3151 Efficient model for coding and agents
31503152 
31513153 - `"claude-fable-5"`
31523154 
from line 3208
32063208 
32073209 New class of intelligence, strongest in coding and cybersecurity
32083210 
3211 - `string`
3212 
32093213 - `name: "advisor"`
32103214 
32113215 Name of the tool.
from line 3844
38403844 
38413845 - `"fast"`
38423846 
3843 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null`
3847 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
38443848 
38453849 - `BetaThinkingConfigEnabled object`
38463850 
from line 3886
38823886 
38833887 - `type: "disabled"`
38843888 
3889 - `BetaThinkingConfigBetweenTools object`
3890 
3891 - `type: "between_tools"`
3892 
38853893 - `BetaThinkingConfigAdaptive object`
38863894 
38873895 - `type: "adaptive"`
from line 3978
39703978 
39713979 - `stream: optional boolean`
39723980 
3973 Whether to incrementally stream the response using server-sent events.
3981 Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
39743982 
3975 See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
3983 In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming#streaming-with-sdks) for an example in each language.
39763984 
39773985 - `system: optional string or array of BetaTextBlockParam`
39783986 
from line 4016
40084016 
40094017 - `BetaThinkingConfigDisabled object`
40104018 
4019 - `BetaThinkingConfigBetweenTools object`
4020 
40114021 - `BetaThinkingConfigAdaptive object`
40124022 
40134023 - `tool_choice: optional BetaToolChoice`
from line 7336
73267336 
73277337 The X11 display number (e.g. 0, 1) for the display.
73287338 
7329 minimum: 0
7330 
7331 - `input_examples: optional array of map[unknown]`
7332 
7333 - `strict: optional boolean`
7334 
7335 When true, guarantees schema validation on tool names and inputs
7336 
7337 - `BetaToolTextEditor20241022 object`
7338 
7339 - `type: "text_editor_20241022"`
7340 
7341 - `name: "str_replace_editor"`
7342 
7343 Name of the tool.
7344 
7345 This is how the tool will be called by the model and
7339

api/beta/messages/batches/create Changed · +94 / -84 lines

from line 3122
31223122 
31233123 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31243124 
3125 - `string`
3125 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
31263126 
3127 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
3128 
31293127 The model that will complete your prompt.
31303128 
31313129 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31323130 
3131 - `"claude-sonnet-5-5"`
3132 
3133 Efficient model for coding and agents
3134 
31333135 - `"claude-fable-5-1"`
31343136 
31353137 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 3146
31443146 
31453147 - `"claude-sonnet-5"`
31463148 
3147 High-performance model for coding and agents
3149 Efficient model for coding and agents
31483150 
31493151 - `"claude-fable-5"`
31503152 
from line 3206
32043206 
32053207 New class of intelligence, strongest in coding and cybersecurity
32063208 
3209 - `string`
3210 
32073211 - `name: "advisor"`
32083212 
32093213 Name of the tool.
from line 3842
38383842 
38393843 - `"fast"`
38403844 
3841 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null`
3845 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
38423846 
38433847 - `BetaThinkingConfigEnabled object`
38443848 
from line 3884
38803884 
38813885 - `type: "disabled"`
38823886 
3887 - `BetaThinkingConfigBetweenTools object`
3888 
3889 - `type: "between_tools"`
3890 
38833891 - `BetaThinkingConfigAdaptive object`
38843892 
38853893 - `type: "adaptive"`
from line 3976
39683976 
39693977 - `stream: optional boolean`
39703978 
3971 Whether to incrementally stream the response using server-sent events.
3979 Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
39723980 
3973 See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
3981 In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming#streaming-with-sdks) for an example in each language.
39743982 
39753983 - `system: optional string or array of BetaTextBlockParam`
39763984 
from line 4013
40054013 - `BetaThinkingConfigEnabled object`
40064014 
40074015 - `BetaThinkingConfigDisabled object`
4016 
4017 - `BetaThinkingConfigBetweenTools object`
40084018 
40094019 - `BetaThinkingConfigAdaptive object`
40104020 

api/beta/messages/batches/results Changed · +84 / -80 lines

from line 2886
28862886 
28872887 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
28882888 
2889 - `string`
2889 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
28902890 
2891 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
2892 
28932891 The model that will complete your prompt.
28942892 
28952893 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
28962894 
2895 - `"claude-sonnet-5-5"`
2896 
2897 Efficient model for coding and agents
2898 
28972899 - `"claude-fable-5-1"`
28982900 
28992901 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 2910
29082910 
29092911 - `"claude-sonnet-5"`
29102912 
2911 High-performance model for coding and agents
2913 Efficient model for coding and agents
29122914 
29132915 - `"claude-fable-5"`
29142916 
from line 2969
29672969 **Deprecated**: Will reach end-of-life on June 30, 2026. Please migrate to claude-mythos-5. Visit https://docs.anthropic.com/en/docs/resources/model-deprecations for more information.
29682970 
29692971 New class of intelligence, strongest in coding and cybersecurity
2972 
2973 - `string`
29702974 
29712975 - `name: "advisor"`
29722976 

api/beta/messages/count_tokens Changed · +88 / -80 lines

from line 3090
30903090 
30913091 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
30923092 
3093 - `string`
3093 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
30943094 
3095 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
3096 
30973095 The model that will complete your prompt.
30983096 
30993097 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31003098 
3099 - `"claude-sonnet-5-5"`
3100 
3101 Efficient model for coding and agents
3102 
31013103 - `"claude-fable-5-1"`
31023104 
31033105 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 3114
31123114 
31133115 - `"claude-sonnet-5"`
31143116 
3115 High-performance model for coding and agents
3117 Efficient model for coding and agents
31163118 
31173119 - `"claude-fable-5"`
31183120 
from line 3174
31723174 
31733175 New class of intelligence, strongest in coding and cybersecurity
31743176 
3177 - `string`
3178 
31753179 - `name: "advisor"`
31763180 
31773181 Name of the tool.
from line 3788
37843788 - `BetaThinkingConfigDisabled object`
37853789 
37863790 - `type: "disabled"`
3791 
3792 - `BetaThinkingConfigBetweenTools object`
3793 
3794 - `type: "between_tools"`
37873795 
37883796 - `BetaThinkingConfigAdaptive object`
37893797 

api/beta/messages/create Changed · +179 / -165 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 3102
31023102 
31033103 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31043104 
3105 - `string`
3105 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
31063106 
3107 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
3108 
31093107 The model that will complete your prompt.
31103108 
31113109 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
31123110 
3111 - `"claude-sonnet-5-5"`
3112 
3113 Efficient model for coding and agents
3114 
31133115 - `"claude-fable-5-1"`
31143116 
31153117 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 3126
31243126 
31253127 - `"claude-sonnet-5"`
31263128 
3127 High-performance model for coding and agents
3129 Efficient model for coding and agents
31283130 
31293131 - `"claude-fable-5"`
31303132 
from line 3186
31843186 
31853187 New class of intelligence, strongest in coding and cybersecurity
31863188 
3189 - `string`
3190 
31873191 - `name: "advisor"`
31883192 
31893193 Name of the tool.
from line 3822
38183822 
38193823 - `"fast"`
38203824 
3821 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigAdaptive or null`
3825 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
38223826 
38233827 - `BetaThinkingConfigEnabled object`
38243828 
from line 3864
38603864 
38613865 - `type: "disabled"`
38623866 
3867 - `BetaThinkingConfigBetweenTools object`
3868 
3869 - `type: "between_tools"`
3870 
38633871 - `BetaThinkingConfigAdaptive object`
38643872 
38653873 - `type: "adaptive"`
from line 3956
39483956 
39493957- `stream: optional boolean`
39503958 
3951 Whether to incrementally stream the response using server-sent events.
3959 Whether to incrementally stream the response using server-sent events. When `true`, SDKs return a raw event stream.
39523960 
3953 See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.
3961 In the TypeScript, Python and Ruby SDKs, the recommended way to stream is `messages.stream()`. It sets `stream` for you and accumulates the events into the final message. See [Streaming with SDKs](https://platform.claude.com/docs/en/build-with-claude/streaming#streaming-with-sdks) for an example in each language.
39543962 
39553963- `system: optional string or array of BetaTextBlockParam`
39563964 
from line 3994
39863994 
39873995 - `BetaThinkingConfigDisabled object`
39883996 
3997 - `BetaThinkingConfigBetweenTools object`
3998 
39893999 - `BetaThinkingConfigAdaptive object`
39904000 
39914001- `tool_choice: optional BetaToolChoice`
from line 6970
69606970 
69616971 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
69626972 
6963 - `string`
6973 - `"claude-sonnet-5-5" or "claude-fable-5-1" or "claude-opus-5-5" or 16 more`
69646974 
6965 - `"claude-fable-5-1" or "claude-opus-5-5" or "claude-mythos-5-1" or 15 more`
6966 
69676975 The model that will complete your prompt.
69686976 
69696977 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
69706978 
6979 - `"claude-sonnet-5-5"`
6980 
6981 Efficient model for coding and agents
6982 
69716983 - `"claude-fable-5-1"`
69726984 
69736985 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
from line 6994
69826994 
69836995 - `"claude-sonnet-5"`
69846996 
6985 High-performance model for coding and agents
6997 Efficient model for coding and agents
69866998 
69876999 - `"claude-fable-5"`
69887000 
from line 7054
70427054 
70437055 New class of intelligence, strongest in coding and cybersecurity
70447056 
7057 - `string`
7058 
70457059 - `name: "advisor"`
70467060 
70477061 Name of the tool.
from line 7201
71877201 
71887202 - `default_config: optional BetaMCPToolDefaultConfig`
71897203 
7190 Default configuration applied to all tools from this server
7191 
7192 - `defer_loading: optional boolean`
7193 
7194 - `enabled: optional boolean`
7195 
7196 - `tools: optional array of BetaMCPToolParam or null`
7197 
7198 The server's tool listing, pinned: when present, the server is not asked for its tools before sampling and exactly these entries, with `default_config` and `configs` applied, are the toolset's tools. Copy it from the `mcp_tool_listing` block of an earlier response.
7199 
7200 - `input_schema: map[unknown]`
7201 
7202 The tool's input schema as the MCP server lists it, verbatim.
7203 
7204 - `name: st
7204 Default configuration applied to all tools from this serve

api/beta/organization Changed · +195 / -17 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.

Nothing in the body moved in this read. What changed is above.

api/beta/organization/analytics Changed · +321 / -11 lines

from line 12
1212Get organization-wide activity summaries for a date range.
1313 
1414Returns one entry per day from `starting_date` (inclusive) to `ending_date`
15(exclusive). Data is typically available with a 1-day lag and may be
16revised by a few percent over the following days: when `ending_date` is
17omitted it defaults to the most recent available day + 1, so the last
18entry covers the most recent available day. The series can be scoped to
19an RBAC group via `filter[]=rbac_group_id:{id}`. Available to
20organizations on a Claude Enterprise plan. Requires an API key with the
21`read:analytics` scope.
15(exclusive) in `data`, the same `data` / `next_page` envelope as the other
16analytics list endpoints; the series is currently returned in full, so
17`next_page` is always null (`summaries` is a deprecated alias of `data`).
18Data is typically available with a 1-day lag and may be revised by a few
19percent over the following days: when `ending_date` is omitted it
20defaults to the most recent available day + 1, so the last entry covers
21the most recent available day. The series can be scoped to an RBAC group
22via `filter[]=rbac_group_id:{id}`. Available to organizations on a Claude
23Enterprise plan. Requires an API key with the `read:analytics` scope.
2224 
2325### Query parameters
2426 
from line 42
4042 
4143 maxItems: 100
4244 
45- `limit: optional number`
46 
47 Number of results per page (1-1000, default 100). The day series (at most 366 entries) is currently returned in full in a single page, so `limit` does not yet shorten it.
48 
49 minimum: 1, maximum: 1000
50 
51- `page: optional string`
52 
53 Opaque cursor from a previous response's `next_page` field. `next_page` is currently always null, so there is never a cursor to send.
54 
4355### Returns
4456 
4557- `BetaActivitySummary object`
from line 58
4658 
4759 Response for GET /v1/organizations/analytics/summaries.
4860 
61 - `data: array of object`
62 
63 One entry per day in the requested range, ascending by date.
64 
65 - `assigned_seat_count: number or null`
66 
67 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
68 
69 - `cowork_daily_active_user_count: number`
70 
71 Number of users with Cowork activity on the requested day
72 
73 - `cowork_monthly_active_user_count: number`
74 
75 Number of users with Cowork activity in the 30-day rolling window
76 
77 - `cowork_weekly_active_user_count: number`
78 
79 Number of users with Cowork activity in the 7-day rolling window
80 
81 - `daily_active_user_count: number`
82 
83 Number of users with token consumption on the requested day
84 
85 - `daily_adoption_rate: number or null`
86 
87 Percentage of assigned seats with activity on the requested day (`DAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
88 
89 - `ending_at: string`
90 
91 End of the aggregation period (exclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-16T00:00:00Z`).
92 
93 format: date-time
94 
95 - `monthly_active_user_count: number`
96 
97 Number of users with token consumption in the 30-day rolling window
98 
99 - `monthly_adoption_rate: number or null`
100 
101 Percentage of assigned seats with activity in the 30-day rolling window (`MAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
102 
103 - `pending_invite_count: number or null`
104 
105 Number of pending invitations to join the organization. Null when the response is scoped to an RBAC group.
106 
107 - `starting_at: string`
108 
109 Start of the aggregation period (inclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-15T00:00:00Z`).
110 
111 format: date-time
112 
113 - `weekly_active_user_count: number`
114 
115 Number of users with token consumption in the 7-day rolling window
116 
117 - `weekly_adoption_rate: number or null`
118 
119 Percentage of assigned seats with activity in the 7-day rolling window (`WAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
120 
121 - `chat_daily_active_user_count: optional number or null`
122 
123 Number of users with claude.ai (chat) activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
124 
125 - `chat_monthly_active_user_count: optional number or null`
126 
127 Number of users with claude.ai (chat) activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
128 
129 - `chat_weekly_active_user_count: optional number or null`
130 
131 Number of users with claude.ai (chat) activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
132 
133 - `claude_code_daily_active_user_count: optional number or null`
134 
135 Number of users with Claude Code activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
136 
137 - `claude_code_monthly_active_user_count: optional number or null`
138 
139 Number of users with Claude Code activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
140 
141 - `claude_code_weekly_active_user_count: optional number or null`
142 
143 Number of users with Claude Code activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
144 
145 - `claude_design_daily_active_user_count: optional number or null`
146 
147 Number of users with Claude Design activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
148 
149 - `claude_design_monthly_active_user_count: optional number or null`
150 
151 Number of users with Claude Design activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
152 
153 - `claude_design_weekly_active_user_count: optional number or null`
154 
155 Number of users with Claude Design activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
156 
157 - `office_agent_daily_active_user_count: optional number or null`
158 
159 Number of users with Claude in Office activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
160 
161 - `office_agent_monthly_active_user_count: optional number or null`
162 
163 Number of users with Claude in Office activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
164 
165 - `office_agent_weekly_active_user_count: optional number or null`
166 
167 Number of users with Claude in Office activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
168 
169 - `science_daily_active_user_count: optional number or null`
170 
171 Number of users with Claude Science activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
172 
173 - `science_entitled_user_count: optional number or null`
174 
175 Number of users with a Claude Science seat entitlement (per-seat RBAC) at the time of the daily snapshot. The funnel top; independent of the org-level Claude Science toggle. Null when the response is scoped to an RBAC group — entitlement is org-wide and has no per-group analogue. Omitted from the response while the per-product breakdown is not enabled for this organization.
176 
177 - `science_monthly_active_user_count: optional number or null`
178 
179 Number of users with Claude Science activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
180 
181 - `science_weekly_active_user_count: optional number or null`
182 
183 Number of users with Claude Science activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
184 
185 - `next_page: string or null`
186 
187 Opaque cursor for the next page, or null if no more results. Currently always null: the day series is returned in full.
188 
49189 - `summaries: array of object`
50190 
191 **Deprecated**
192 
193 Deprecated: use `data`, which carries the same entries.
194 
51195 - `assigned_seat_count: number or null`
52196 
53197 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
from line 324
180324 
181325```json
182326{
327 "data": [
328 {
329 "assigned_seat_count": 0,
330 "cowork_daily_active_user_count": 0,
331 "cowork_monthly_active_user_count": 0,
332 "cowork_weekly_active_user_count": 0,
333 "daily_active_user_count": 0,
334 "daily_adoption_rate": 0,
335 "ending_at": "2019-12-27T18:11:19.117Z",
336 "monthly_active_user_count": 0,
337 "monthly_adoption_rate": 0,
338 "pending_invite_count": 0,
339 "starting_at": "2019-12-27T18:11:19.117Z",
340 "weekly_active_user_count": 0,
341 "weekly_adoption_rate": 0,
342 "chat_daily_active_user_count": 0,
343 "chat_monthly_active_user_count": 0,
344 "chat_weekly_active_user_count": 0,
345 "claude_code_daily_active_user_count": 0,
346 "claude_code_monthly_active_user_count": 0,
347 "claude_code_weekly_active_user_count": 0,
348 "claude_design_daily_active_user_count": 0,
349 "claude_design_monthly_active_user_count": 0,
350 "claude_design_weekly_active_user_count": 0,
351 "office_agent_daily_active_user_count": 0,
352 "office_agent_monthly_active_user_count": 0,
353 "office_agent_weekly_active_user_count": 0,
354 "science_daily_active_user_count": 0,
355 "science_entitled_user_count": 0,
356 "science_monthly_active_user_count": 0,
357 "science_weekly_active_user_count": 0
358 }
359 ],
360 "next_page": "next_page",
183361 "summaries": [
184362 {
185363 "assigned_seat_count": 0,
from line 402
224402 
225403 Response for GET /v1/organizations/analytics/summaries.
226404 
405 - `data: array of object`
406 
407 One entry per day in the requested range, ascending by date.
408 
409 - `assigned_seat_count: number or null`
410 
411 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
412 
413 - `cowork_daily_active_user_count: number`
414 
415 Number of users with Cowork activity on the requested day
416 
417 - `cowork_monthly_active_user_count: number`
418 
419 Number of users with Cowork activity in the 30-day rolling window
420 
421 - `cowork_weekly_active_user_count: number`
422 
423 Number of users with Cowork activity in the 7-day rolling window
424 
425 - `daily_active_user_count: number`
426 
427 Number of users with token consumption on the requested day
428 
429 - `daily_adoption_rate: number or null`
430 
431 Percentage of assigned seats with activity on the requested day (`DAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
432 
433 - `ending_at: string`
434 
435 End of the aggregation period (exclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-16T00:00:00Z`).
436 
437 format: date-time
438 
439 - `monthly_active_user_count: number`
440 
441 Number of users with token consumption in the 30-day rolling window
442 
443 - `monthly_adoption_rate: number or null`
444 
445 Percentage of assigned seats with activity in the 30-day rolling window (`MAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
446 
447 - `pending_invite_count: number or null`
448 
449 Number of pending invitations to join the organization. Null when the response is scoped to an RBAC group.
450 
451 - `starting_at: string`
452 
453 Start of the aggregation period (inclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-15T00:00:00Z`).
454 
455 format: date-time
456 
457 - `weekly_active_user_count: number`
458 
459 Number of users with token consumption in the 7-day rolling window
460 
461 - `weekly_adoption_rate: number or null`
462 
463 Percentage of assigned seats with activity in the 7-day rolling window (`WAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
464 
465 - `chat_daily_active_user_count: optional number or null`
466 
467 Number of users with claude.ai (chat) activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
468 
469 - `chat_monthly_active_user_count: optional number or null`
470 
471 Number of users with claude.ai (chat) activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
472 
473 - `chat_weekly_active_user_count: optional number or null`
474 
475 Number of users with claude.ai (chat) activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
476 
477 - `claude_code_daily_active_user_count: optional number or null`
478 
479 Number of users with Claude Code activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
480 
481 - `claude_code_monthly_active_user_count: optional number or null`
482 
483 Number of users with Claude Code activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
484 
485 - `claude_code_weekly_active_user_count: optional number or null`
486 
487 Number of users with Claude Code activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
488 
489 - `claude_design_daily_active_user_count: optional number or null`
490 
491 Number of users with Claude Design activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
492 
493 - `claude_design_monthly_active_user_count: optional number or null`
494 
495 Number of users with Claude Design activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
496 
497 - `claude_design_weekly_active_user_count: optional number or null`
498 
499 Number of users with Claude Design activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
500 
501 - `office_agent_daily_active_user_count: optional number or null`
502 
503 Number of users with Claude in Office activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
504 
505 - `office_agent_monthly_active_user_count: optional number or null`
506 
507 Number of users with Claude in Office activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
508 
509 - `office_agent_weekly_active_user_count: optional number or null`
510 
511 Number of users with Claude in Office activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
512 
513 - `science_daily_active_user_count: optional number or null`
514 
515 Number of users with Claude Science activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
516 
517 - `science_entitled_user_count: optional number or null`
518 
519 Number of users with a Claude Science seat entitlement (per-seat RBAC) at the time of the daily snapshot. The funnel top; independent of the org-level Claude Science toggle. Null when the response is scoped to an RBAC group — entitlement is org-wide and has no per-group analogue. Omitted from the response while the per-product breakdown is not enabled for this organization.
520 
521 - `science_monthly_active_user_count: optional number or null`
522 
523 Number of users with Claude Science activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
524 
525 - `science_weekly_active_user_count: optional number or null`
526 
527 Number of users with Claude Science activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
528 
529 - `next_page: string or null`
530 
531 Opaque cursor for the next page, or null if no more results. Currently always null: the day series is returned in full.
532 
227533 - `summaries: array of object`
228534 
535 **Deprecated**
536 
537 Deprecated: use `data`, which carries the same entries.
538 
229539 - `assigned_seat_count: number or null`
230540 
231541 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
from line 1774
14641774 
14651775 - `"web_search"`
14661776 
1467 - `currency: "USD"`
1777 - `currency: string`
14681778 
14691779 Currency code for the cost amount. Currently always `"USD"`.
14701780 
from line 2174
18642174 
18652175 - `"web_search"`
18662176 
1867 - `currency: "USD"`
2177 - `currency: string`
18682178 
18692179 Currency code for the cost amount. Currently always `"USD"`.
18702180 
from line 2990
26802990 
26812991 List-price (rate-card) value of the member requests attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD), from Claude Code, Cowork, and Office Agent request-level attribution — the value of requests that involved the skill, not the skill's incremental cost. Unlike `estimated_overage_spend` this reflects usage value regardless of how it was funded — seat-covered usage counts — but it is undiscounted and does not tie to billed spend or the organization's spend reporting. claude.ai chat usage carries no request-level attribution and contributes nothing: the field is null on `chat` product rows and on `office_agent` product cuts dated before 2026-06-18 (the Office Agent attribution data-start), and on ungrouped rows it covers the Claude Code + Cowork + Office Agent share only (null when no attributable usage exists). Also null under the same conditions as `estimated_overage_spend` (spend reporting not enabled for this organization, `office_agent` product cuts before the 2026-06-18 data-start). "0" means attributable usage existed but none was attributed to this skill. Addable across days: date-range rollup mode returns the window's sum. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts.
26822992 
2683 - `currency: optional "USD" or null`
2993 - `currency: optional string or null`
26842994 
26852995 Currency for this row's monetary fields (`estimated_overage_spend` and `attributed_list_price`), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null.
26862996 
from line 3080
27703080 },
27713081 "skill_name": "skill_name",
27723082 "attributed_list_price": "attributed_list_price",
2773 "currency": "USD",
3083 "currency": "currency",
27743084 "enable_count": 0,
27753085 "estimated_overage_spend": "estimated_overage_spend",
27763086 "invocation_count": 0,

api/beta/organization/analytics/cost Changed · +4 / -4 lines

from line 236
236236 
237237 - `"web_search"`
238238 
239 - `currency: "USD"`
239 - `currency: string`
240240 
241241 Currency code for the cost amount. Currently always `"USD"`.
242242 
from line 636
636636 
637637 - `"web_search"`
638638 
639 - `currency: "USD"`
639 - `currency: string`
640640 
641641 Currency code for the cost amount. Currently always `"USD"`.
642642 
from line 833
833833 
834834 - `"web_search"`
835835 
836 - `currency: "USD"`
836 - `currency: string`
837837 
838838 Currency code for the cost amount. Currently always `"USD"`.
839839 
from line 989
989989 
990990 - `"web_search"`
991991 
992 - `currency: "USD"`
992 - `currency: string`
993993 
994994 Currency code for the cost amount. Currently always `"USD"`.
995995 

api/beta/organization/analytics/retrieve_summaries Changed · +185 / -7 lines

from line 10
1010Get organization-wide activity summaries for a date range.
1111 
1212Returns one entry per day from `starting_date` (inclusive) to `ending_date`
13(exclusive). Data is typically available with a 1-day lag and may be
14revised by a few percent over the following days: when `ending_date` is
15omitted it defaults to the most recent available day + 1, so the last
16entry covers the most recent available day. The series can be scoped to
17an RBAC group via `filter[]=rbac_group_id:{id}`. Available to
18organizations on a Claude Enterprise plan. Requires an API key with the
19`read:analytics` scope.
13(exclusive) in `data`, the same `data` / `next_page` envelope as the other
14analytics list endpoints; the series is currently returned in full, so
15`next_page` is always null (`summaries` is a deprecated alias of `data`).
16Data is typically available with a 1-day lag and may be revised by a few
17percent over the following days: when `ending_date` is omitted it
18defaults to the most recent available day + 1, so the last entry covers
19the most recent available day. The series can be scoped to an RBAC group
20via `filter[]=rbac_group_id:{id}`. Available to organizations on a Claude
21Enterprise plan. Requires an API key with the `read:analytics` scope.
2022 
2123## Query parameters
2224 
from line 40
3840 
3941 maxItems: 100
4042 
43- `limit: optional number`
44 
45 Number of results per page (1-1000, default 100). The day series (at most 366 entries) is currently returned in full in a single page, so `limit` does not yet shorten it.
46 
47 minimum: 1, maximum: 1000
48 
49- `page: optional string`
50 
51 Opaque cursor from a previous response's `next_page` field. `next_page` is currently always null, so there is never a cursor to send.
52 
4153## Returns
4254 
4355- `BetaActivitySummary object`
from line 56
4456 
4557 Response for GET /v1/organizations/analytics/summaries.
4658 
59 - `data: array of object`
60 
61 One entry per day in the requested range, ascending by date.
62 
63 - `assigned_seat_count: number or null`
64 
65 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
66 
67 - `cowork_daily_active_user_count: number`
68 
69 Number of users with Cowork activity on the requested day
70 
71 - `cowork_monthly_active_user_count: number`
72 
73 Number of users with Cowork activity in the 30-day rolling window
74 
75 - `cowork_weekly_active_user_count: number`
76 
77 Number of users with Cowork activity in the 7-day rolling window
78 
79 - `daily_active_user_count: number`
80 
81 Number of users with token consumption on the requested day
82 
83 - `daily_adoption_rate: number or null`
84 
85 Percentage of assigned seats with activity on the requested day (`DAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
86 
87 - `ending_at: string`
88 
89 End of the aggregation period (exclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-16T00:00:00Z`).
90 
91 format: date-time
92 
93 - `monthly_active_user_count: number`
94 
95 Number of users with token consumption in the 30-day rolling window
96 
97 - `monthly_adoption_rate: number or null`
98 
99 Percentage of assigned seats with activity in the 30-day rolling window (`MAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
100 
101 - `pending_invite_count: number or null`
102 
103 Number of pending invitations to join the organization. Null when the response is scoped to an RBAC group.
104 
105 - `starting_at: string`
106 
107 Start of the aggregation period (inclusive), UTC midnight in RFC 3339 format (e.g. `2026-01-15T00:00:00Z`).
108 
109 format: date-time
110 
111 - `weekly_active_user_count: number`
112 
113 Number of users with token consumption in the 7-day rolling window
114 
115 - `weekly_adoption_rate: number or null`
116 
117 Percentage of assigned seats with activity in the 7-day rolling window (`WAU / assigned_seat_count * 100`). Null when the response is scoped to an RBAC group.
118 
119 - `chat_daily_active_user_count: optional number or null`
120 
121 Number of users with claude.ai (chat) activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
122 
123 - `chat_monthly_active_user_count: optional number or null`
124 
125 Number of users with claude.ai (chat) activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
126 
127 - `chat_weekly_active_user_count: optional number or null`
128 
129 Number of users with claude.ai (chat) activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
130 
131 - `claude_code_daily_active_user_count: optional number or null`
132 
133 Number of users with Claude Code activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
134 
135 - `claude_code_monthly_active_user_count: optional number or null`
136 
137 Number of users with Claude Code activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
138 
139 - `claude_code_weekly_active_user_count: optional number or null`
140 
141 Number of users with Claude Code activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
142 
143 - `claude_design_daily_active_user_count: optional number or null`
144 
145 Number of users with Claude Design activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
146 
147 - `claude_design_monthly_active_user_count: optional number or null`
148 
149 Number of users with Claude Design activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
150 
151 - `claude_design_weekly_active_user_count: optional number or null`
152 
153 Number of users with Claude Design activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
154 
155 - `office_agent_daily_active_user_count: optional number or null`
156 
157 Number of users with Claude in Office activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
158 
159 - `office_agent_monthly_active_user_count: optional number or null`
160 
161 Number of users with Claude in Office activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
162 
163 - `office_agent_weekly_active_user_count: optional number or null`
164 
165 Number of users with Claude in Office activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
166 
167 - `science_daily_active_user_count: optional number or null`
168 
169 Number of users with Claude Science activity on the requested day. Omitted from the response while the per-product breakdown is not enabled for this organization.
170 
171 - `science_entitled_user_count: optional number or null`
172 
173 Number of users with a Claude Science seat entitlement (per-seat RBAC) at the time of the daily snapshot. The funnel top; independent of the org-level Claude Science toggle. Null when the response is scoped to an RBAC group — entitlement is org-wide and has no per-group analogue. Omitted from the response while the per-product breakdown is not enabled for this organization.
174 
175 - `science_monthly_active_user_count: optional number or null`
176 
177 Number of users with Claude Science activity in the 30-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
178 
179 - `science_weekly_active_user_count: optional number or null`
180 
181 Number of users with Claude Science activity in the 7-day rolling window. Omitted from the response while the per-product breakdown is not enabled for this organization.
182 
183 - `next_page: string or null`
184 
185 Opaque cursor for the next page, or null if no more results. Currently always null: the day series is returned in full.
186 
47187 - `summaries: array of object`
48188 
189 **Deprecated**
190 
191 Deprecated: use `data`, which carries the same entries.
192 
49193 - `assigned_seat_count: number or null`
50194 
51195 Number of seats currently assigned to members. Null when the response is scoped to an RBAC group — seat assignment is org-wide and has no per-group analogue.
from line 322
178322 
179323```json
180324{
325 "data": [
326 {
327 "assigned_seat_count": 0,
328 "cowork_daily_active_user_count": 0,
329 "cowork_monthly_active_user_count": 0,
330 "cowork_weekly_active_user_count": 0,
331 "daily_active_user_count": 0,
332 "daily_adoption_rate": 0,
333 "ending_at": "2019-12-27T18:11:19.117Z",
334 "monthly_active_user_count": 0,
335 "monthly_adoption_rate": 0,
336 "pending_invite_count": 0,
337 "starting_at": "2019-12-27T18:11:19.117Z",
338 "weekly_active_user_count": 0,
339 "weekly_adoption_rate": 0,
340 "chat_daily_active_user_count": 0,
341 "chat_monthly_active_user_count": 0,
342 "chat_weekly_active_user_count": 0,
343 "claude_code_daily_active_user_count": 0,
344 "claude_code_monthly_active_user_count": 0,
345 "claude_code_weekly_active_user_count": 0,
346 "claude_design_daily_active_user_count": 0,
347 "claude_design_monthly_active_user_count": 0,
348 "claude_design_weekly_active_user_count": 0,
349 "office_agent_daily_active_user_count": 0,
350 "office_agent_monthly_active_user_count": 0,
351 "office_agent_weekly_active_user_count": 0,
352 "science_daily_active_user_count": 0,
353 "science_entitled_user_count": 0,
354 "science_monthly_active_user_count": 0,
355 "science_weekly_active_user_count": 0
356 }
357 ],
358 "next_page": "next_page",
181359 "summaries": [
182360 {
183361 "assigned_seat_count": 0,

api/beta/organization/analytics/skills Changed · +3 / -3 lines

from line 146
146146 
147147 List-price (rate-card) value of the member requests attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD), from Claude Code, Cowork, and Office Agent request-level attribution — the value of requests that involved the skill, not the skill's incremental cost. Unlike `estimated_overage_spend` this reflects usage value regardless of how it was funded — seat-covered usage counts — but it is undiscounted and does not tie to billed spend or the organization's spend reporting. claude.ai chat usage carries no request-level attribution and contributes nothing: the field is null on `chat` product rows and on `office_agent` product cuts dated before 2026-06-18 (the Office Agent attribution data-start), and on ungrouped rows it covers the Claude Code + Cowork + Office Agent share only (null when no attributable usage exists). Also null under the same conditions as `estimated_overage_spend` (spend reporting not enabled for this organization, `office_agent` product cuts before the 2026-06-18 data-start). "0" means attributable usage existed but none was attributed to this skill. Addable across days: date-range rollup mode returns the window's sum. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts.
148148 
149 - `currency: optional "USD" or null`
149 - `currency: optional string or null`
150150 
151151 Currency for this row's monetary fields (`estimated_overage_spend` and `attributed_list_price`), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null.
152152 
from line 236
236236 },
237237 "skill_name": "skill_name",
238238 "attributed_list_price": "attributed_list_price",
239 "currency": "USD",
239 "currency": "currency",
240240 "enable_count": 0,
241241 "estimated_overage_spend": "estimated_overage_spend",
242242 "invocation_count": 0,
from line 322
322322 
323323 List-price (rate-card) value of the member requests attributed to this skill, as a decimal string in the minor unit of `currency` (cents for USD), from Claude Code, Cowork, and Office Agent request-level attribution — the value of requests that involved the skill, not the skill's incremental cost. Unlike `estimated_overage_spend` this reflects usage value regardless of how it was funded — seat-covered usage counts — but it is undiscounted and does not tie to billed spend or the organization's spend reporting. claude.ai chat usage carries no request-level attribution and contributes nothing: the field is null on `chat` product rows and on `office_agent` product cuts dated before 2026-06-18 (the Office Agent attribution data-start), and on ungrouped rows it covers the Claude Code + Cowork + Office Agent share only (null when no attributable usage exists). Also null under the same conditions as `estimated_overage_spend` (spend reporting not enabled for this organization, `office_agent` product cuts before the 2026-06-18 data-start). "0" means attributable usage existed but none was attributed to this skill. Addable across days: date-range rollup mode returns the window's sum. On `group_by[]` and `filter[]` shapes both amounts can total below the ungrouped value for the same skill over the same date or range: spend attributed to a member–skill pair with no counted usage on that day is excluded from those cuts.
324324 
325 - `currency: optional "USD" or null`
325 - `currency: optional string or null`
326326 
327327 Currency for this row's monetary fields (`estimated_overage_spend` and `attributed_list_price`), as an uppercase ISO-4217 code. Always "USD" when either amount is populated; null whenever both amounts are null.
328328 

api/beta/organization/mcp_tunnels Changed · +8 / -8 lines

from line 189
189189 
190190 - `workspace_id: string or null`
191191 
192 ID of the Workspace this Tunnel belongs to, or `null` for the default
193 Workspace. Immutable after creation.
192 ID of the Workspace this Tunnel belongs to. May be `null` for a Tunnel in
193 the default Workspace. A Tunnel never moves to another Workspace.
194194 
195195- `next_page: string or null`
196196 
from line 385
385385 
386386 - `workspace_id: string or null`
387387 
388 ID of the Workspace this Tunnel belongs to, or `null` for the default
389 Workspace. Immutable after creation.
388 ID of the Workspace this Tunnel belongs to. May be `null` for a Tunnel in
389 the default Workspace. A Tunnel never moves to another Workspace.
390390 
391391### Example
392392 
from line 577
577577 
578578 - `workspace_id: string or null`
579579 
580 ID of the Workspace this Tunnel belongs to, or `null` for the default
581 Workspace. Immutable after creation.
580 ID of the Workspace this Tunnel belongs to. May be `null` for a Tunnel in
581 the default Workspace. A Tunnel never moves to another Workspace.
582582 
583583### Example
584584 
from line 984
984984 
985985 - `workspace_id: string or null`
986986 
987 ID of the Workspace this Tunnel belongs to, or `null` for the default
988 Workspace. Immutable after creation.
987 ID of the Workspace this Tunnel belongs to. May be `null` for a Tunnel in
988 the default Workspace. A Tunnel never moves to another Workspace.
989989 
990990### Beta Organization Tunnel Token
991991 

api/beta/sessions Changed · +8125 / -7985 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 183
183183 
184184 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
185185 
186 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
186 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
187187 
188188 The model that will power your agent.
189189 
190190 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
191191 
192 - `string`
192 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
193193 
194 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
195 
196194 The model that will power your agent.
197195 
198196 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
199197 
198 - `"claude-sonnet-5-5"`
199 
200 Efficient model for coding and agents
201 
200202 - `"claude-opus-5-5"`
201203 
202204 Powerful intelligence for coding, knowledge work, and long-running agents
from line 209
207209 
208210 - `"claude-sonnet-5"`
209211 
210 High-performance model for coding and agents
212 Efficient model for coding and agents
211213 
212214 - `"claude-fable-5"`
213215 
from line 259
257259 
258260 High-performance model for agents and coding
259261 
262 - `string`
263 
260264 - `BetaManagedAgentsModelConfigParams object`
261265 
262266 An object that defines additional configuration control over model use
from line 1195
11911195 
11921196 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11931197 
1194 - `string`
1198 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
11951199 
1196 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
1197 
11981200 The model that will power your agent.
11991201 
12001202 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
12011203 
1204 - `"claude-sonnet-5-5"`
1205 
1206 Efficient model for coding and agents
1207 
12021208 - `"claude-opus-5-5"`
12031209 
12041210 Powerful intelligence for coding, knowledge work, and long-running agents
from line 1215
12091215 
12101216 - `"claude-sonnet-5"`
12111217 
1212 High-performance model for coding and agents
1218 Efficient model for coding and agents
12131219 
12141220 - `"claude-fable-5"`
12151221 
from line 1265
12591265 
12601266 High-performance model for agents and coding
12611267 
1268 - `string`
1269 
12621270 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
12631271 
12641272 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 2508
25002508 
25012509 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25022510 
2503 - `string`
2511 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
25042512 
2505 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
2506 
25072513 The model that will power your agent.
25082514 
25092515 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
25102516 
2517 - `"claude-sonnet-5-5"`
2518 
2519 Efficient model for coding and agents
2520 
25112521 - `"claude-opus-5-5"`
25122522 
25132523 Powerful intelligence for coding, knowledge work, and long-running agents
from line 2528
25182528 
25192529 - `"claude-sonnet-5"`
25202530 
2521 High-performance model for coding and agents
2531 Efficient model for coding and agents
25222532 
25232533 - `"claude-fable-5"`
25242534 
from line 2578
25682578 
25692579 High-performance model for agents and coding
25702580 
2581 - `string`
2582 
25712583 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
25722584 
25732585 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 3747
37353747 
37363748 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
37373749 
3738 - `string`
3750 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
37393751 
3740 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
3741 
37423752 The model that will power your agent.
37433753 
37443754 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
37453755 
3756 - `"claude-sonnet-5-5"`
3757 
3758 Efficient model for coding and agents
3759 
37463760 - `"claude-opus-5-5"`
37473761 
37483762 Powerful intelligence for coding, knowledge work, and long-running agents
from line 3767
37533767 
37543768 - `"claude-sonnet-5"`
37553769 
3756 High-performance model for coding and agents
3770 Efficient model for coding and agents
37573771 
37583772 - `"claude-fable-5"`
37593773 
from line 3817
38033817 
38043818 High-performance model for agents and coding
38053819 
3820 - `string`
3821 
38063822 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
38073823 
38083824 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 5458
54425458 
54435459 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54445460 
5445 - `string`
5461 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
54465462 
5447 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
5448 
54495463 The model that will power your agent.
54505464 
54515465 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
54525466 
5467 - `"claude-sonnet-5-5"`
5468 
5469 Efficient model for coding and agents
5470 
54535471 - `"claude-opus-5-5"`
54545472 
54555473 Powerful intelligence for coding, knowledge work, and long-running agents
from line 5478
54605478 
54615479 - `"claude-sonnet-5"`
54625480 
5463 High-performance model for coding and agents
5481 Efficient model for coding and agents
54645482 
54655483 - `"claude-fable-5"`
54665484 
from line 5528
55105528 
55115529 High-performance model for agents and coding
55125530 
5531 - `string`
5532 
55135533 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
55145534 
55155535 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 6838
68186838 
68196839 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
68206840 
6821 - `string`
6841 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
68226842 
6823 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
6824 
68256843 The model that will power your agent.
68266844 
68276845 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
68286846 
6847 - `"claude-sonnet-5-5"`
6848 
6849 Efficient model for coding and agents
6850 
68296851 - `"claude-opus-5-5"`
68306852 
68316853 Powerful intelligence for coding, knowledge work, and long-running agents
from line 6858
68366858 
68376859 - `"claude-sonnet-5"`
68386860 
6839 High-performance model for coding and agents
6861 Efficient model for coding and agents
68406862 
68416863 - `"claude-fable-5"`
68426864 
from line 6908
68866908 
68876909 High-performance model for agents and coding
68886910 
6911 - `string`
6912 
68896913 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
68906914 
68916915 How hard Claude works on each inference call. One of `low`, `medium`, `high`, `xhigh`, `max`. Always present; resolved to the per-model default at save time when not supplied.
from line 7996
79727996 
79737997 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
79747998 
7975 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
7999 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
79768000 
79778001 The model that will power your agent.
79788002 
79798003 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
79808004 
7981 - `string`
8005 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
79828006 
7983 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
7984 
79858007 The model that will power your agent.
79868008 
79878009 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
79888010 
8011 - `"claude-sonnet-5-5"`
8012 
8013 Efficient model for coding and agents
8014 
79898015 - `"claude-opus-5-5"`
79908016 
79918017 Powerful intelligence for coding, knowledge work, and long-running agents
from line 8022
79968022 
79978023 - `"claude-sonnet-5"`
79988024 
7999 High-performance model for coding and agents
8025 Efficient model for coding and agents
80008026 
80018027 - `"claude-fable-5"`
80028028 
from line 8072
80468072 
80478073 High-performance model for agents and coding
80488074 
8075 - `string`
8076 
80498077 - `BetaManagedAgentsModelConfigParams object`
80508078 
80518079 An object that defines additional configuration control over model use
from line 8368
83408368 
83418369 - `BetaManagedAgentsAutoPolicy object`
83428370 
8343 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a judgement on evaluates to ask.
8344 
8345 - `BetaManagedAgentsGrepToolConfigParams object`
8346 
8347 Configuration override for the grep tool.
8348 
8349 - `type: optional "grep"`
8350 
8351 - `name: "grep"`
8352 
8353 Must be "grep".
8354 
8355 - `enabled: optional boolean or null`
8356 
8357 Whether this tool is enabled and available to Claude. Overrides the default_config setting.
8358 
8359 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`
8360 
8361 Permission p
8371 The server decides each tool call individually: it judges, from the tool, its input, and the session content so far, whether the call is safe to execute or high-risk, and evaluates it to allow when judged safe and to deny when judged high-risk. A call the server cannot reach a j

api/beta/sessions/archive Changed · +70 / -66 lines

from line 163
163163 
164164 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
165165 
166 - `string`
166 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
167167 
168 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
169 
170168 The model that will power your agent.
171169 
172170 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
173171 
172 - `"claude-sonnet-5-5"`
173 
174 Efficient model for coding and agents
175 
174176 - `"claude-opus-5-5"`
175177 
176178 Powerful intelligence for coding, knowledge work, and long-running agents
from line 183
181183 
182184 - `"claude-sonnet-5"`
183185 
184 High-performance model for coding and agents
186 Efficient model for coding and agents
185187 
186188 - `"claude-fable-5"`
187189 
from line 232
230232 - `"claude-sonnet-4-5-20250929"`
231233 
232234 High-performance model for agents and coding
235 
236 - `string`
233237 
234238 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
235239 

api/beta/sessions/create Changed · +1011 / -1003 lines

from line 181
181181 
182182 Replacement model. Accepts the model string, e.g. `claude-opus-5`, or a `model_config` object. Omit to use the agent's model.
183183 
184 - `BetaManagedAgentsModel = string or "claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
184 - `BetaManagedAgentsModel = "claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more or string`
185185 
186186 The model that will power your agent.
187187 
188188 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
189189 
190 - `string`
190 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
191191 
192 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
193 
194192 The model that will power your agent.
195193 
196194 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
197195 
196 - `"claude-sonnet-5-5"`
197 
198 Efficient model for coding and agents
199 
198200 - `"claude-opus-5-5"`
199201 
200202 Powerful intelligence for coding, knowledge work, and long-running agents
from line 207
205207 
206208 - `"claude-sonnet-5"`
207209 
208 High-performance model for coding and agents
210 Efficient model for coding and agents
209211 
210212 - `"claude-fable-5"`
211213 
from line 257
255257 
256258 High-performance model for agents and coding
257259 
260 - `string`
261 
258262 - `BetaManagedAgentsModelConfigParams object`
259263 
260264 An object that defines additional configuration control over model use
from line 1193
11891193 
11901194 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11911195 
1192 - `string`
1196 - `"claude-sonnet-5-5" or "claude-opus-5-5" or "claude-fable-5-1" or 13 more`
11931197 
1194 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
1195 
11961198 The model that will power your agent.
11971199 
11981200 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
11991201 
1202 - `"claude-sonnet-5-5"`
1203 
1204 Efficient model for coding and agents
1205 
12001206 - `"claude-opus-5-5"`
12011207 
12021208 Powerful intelligence for coding, knowledge work, and long-running agents
from line 1213
12071213 
12081214 - `"claude-sonnet-5"`
12091215 
1210 High-performance model for coding and agents
1216 Efficient model for coding and agents
12111217 
12121218 - `"claude-fable-5"`
12131219 
from line 1262
12561262 - `"claude-sonnet-4-5-20250929"`
12571263 
12581264 High-performance model for agents and coding
1265 
1266 - `string`
12591267 
12601268 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
12611269 
Feedback