Get Session Thread changedapi/beta/sessions/threads/retrieve
Nearest release: v2.1.283, published 3 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+14added
Lines−14removed
From line
141
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits11to this page, all time
The whole hunk
from line 141, old and new numbered
/
from line 141
141141
142142 - `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
143143
144 The resolved agent a `session_thread` runs.
144 Resolved agent definition for this thread. Snapshot of the agent at thread creation time.
145145
146146 - `BetaManagedAgentsSessionThreadAgent object`
147147
from line 171
171171
172172 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
173173
174 - `string`
175
174176 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
175177
176178 The model that will power your agent.
from line 239
237239
238240 High-performance model for agents and coding
239241
240 - `string`
241
242242 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
243243
244 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
244 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.
245245
246246 - `BetaManagedAgentsEffortLow object`
247247
from line 279
279279
280280 - `speed: optional "standard" or "fast"`
281281
282 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Not all models support `fast`; invalid combinations are rejected at create time.
282 Inference speed mode. `fast` provides significantly faster output token generation at premium pricing. Defaults to `standard`. Not all models support `fast`; invalid combinations are rejected at create time.
283283
284284 - `"standard"`
285285
from line 683
683683
684684 - `archived_at: string or null`
685685
686 A timestamp in RFC 3339 format
686 When the thread was archived. Null if not archived.
687687
688688 format: date-time
689689
690690 - `created_at: string`
691691
692 A timestamp in RFC 3339 format
692 When the thread was created.
693693
694694 format: date-time
695695
from line 703
703703
704704 - `stats: BetaManagedAgentsSessionThreadStats or null`
705705
706 Timing statistics for a session thread.
706 Timing statistics for this thread. Null until the thread's first status transition.
707707
708708 - `active_seconds: optional number`
709709
from line 725
725725
726726 - `status: BetaManagedAgentsSessionThreadStatus`
727727
728 SessionThreadStatus enum
728 Current execution status of the thread.
729729
730730 - `"running"`
731731
from line 737
737737
738738 - `updated_at: string`
739739
740 A timestamp in RFC 3339 format
740 When the thread was last updated.
741741
742742 format: date-time
743743
744744 - `usage: BetaManagedAgentsSessionThreadUsage or null`
745745
746 Cumulative token usage for a session thread across all turns.
746 Cumulative token usage for this thread. Null until the thread's first idle transition.
747747
748748 - `active_seconds: optional number`
749749
from line 753
753753
754754 - `cache_creation: optional BetaManagedAgentsCacheCreationUsage`
755755
756 Prompt-cache creation token usage broken down by cache lifetime.
756 Tokens used to create prompt cache entries, broken down by cache TTL.
757757
758758 - `ephemeral_1h_input_tokens: optional number`
759759
from line 781
781781
782782 - `list_cost: optional BetaMonetaryAmount or null`
783783
784 A monetary amount in a specific currency.
784 Cumulative list cost of this thread across all turns, priced at public list rates. Absent until cost tracking is available for the thread. Each figure is rounded to the nearest cent independently and the session's aggregate `usage.list_cost` additionally includes session runtime, so per-thread costs do not sum exactly to the session figure; the session figure is authoritative and is what a budget is enforced against.
785785
786786 - `amount: string`
787787
from line 799
799799
800800 - `server_tool_use: optional BetaManagedAgentsServerToolUsage or null`
801801
802 Cumulative count of server-executed tool invocations, broken down by tool.
802 Cumulative server-executed tool usage across all turns of this thread. Absent until server-tool tracking is available for the thread.
803803
804804 - `web_fetch_requests: optional number`
805805
No line in this hunk matches that.