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

Versions changedapi/beta/agents/versions

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+11added
Lines−11removed
From line 153 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 153, old and new numbered
/
lines
from line 153
153153 
154154 - `archived_at: string or null`
155155 
156 A timestamp in RFC 3339 format
156 When the agent was archived. Null if not archived.
157157 
158158 format: date-time
159159 
from line 185
185185 
186186 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
187187 
188 - `string`
189 
188190 - `"claude-opus-5-5" or "claude-fable-5-1" or "claude-sonnet-5" or 12 more`
189191 
190192 The model that will power your agent.
from line 253
251253 
252254 High-performance model for agents and coding
253255 
254 - `string`
255 
256256 - `effort: optional BetaManagedAgentsEffortLow or BetaManagedAgentsEffortMedium or BetaManagedAgentsEffortHigh or 2 more`
257257 
258 How hard Claude works on each turn. Sets `output_config.effort` on every Messages call the session makes.
258 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.
259259 
260260 - `BetaManagedAgentsEffortLow object`
261261 
from line 293
293293 
294294 - `speed: optional "standard" or "fast"`
295295 
296 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.
296 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.
297297 
298298 - `"standard"`
299299 
from line 301
301301 
302302 - `multiagent: BetaManagedAgentsMultiagent or null`
303303 
304 Resolved coordinator topology with a concrete agent roster.
304 Multiagent orchestration configuration. Null when the agent is single-threaded.
305305 
306306 - `type: "coordinator"`
307307 
Feedback