Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

Agents changed

api/beta/agents

Nearest release: v2.1.280, published 20 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+62added
Lines−0removed
From line 115 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits9to this page, all time

The whole hunk

from line 115, old and new numbered
/
lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 115
115115 
116116- `"anthropic-workspace-id": optional string`
117117 
118 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
119 
120 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
121 
118122### Body parameters
119123 
120124- `model: BetaManagedAgentsModel or BetaManagedAgentsModelConfigParams`
from line 215
211215 
212216 - `"low"`
213217 
218 Low effort. Favors latency over reasoning depth.
219 
214220 - `"medium"`
215221 
222 Medium effort. Balances latency and reasoning depth.
223 
216224 - `"high"`
217225 
226 High effort. Favors reasoning depth.
227 
218228 - `"xhigh"`
219229 
230 Extra-high effort. Not all models accept this level.
231 
220232 - `"max"`
221233 
234 Maximum effort. Favors reasoning depth over latency.
235 
222236 - `BetaManagedAgentsEffortLow object`
223237 
224238 Low effort. Favors latency over reasoning depth.
from line 1652
16381652 
16391653- `"anthropic-workspace-id": optional string`
16401654 
1655 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
1656 
1657 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
1658 
16411659### Returns
16421660 
16431661- `data: array of BetaManagedAgentsAgent`
from line 2341
23232341 
23242342- `agent_id: string`
23252343 
2344 Unique identifier of the agent to retrieve.
2345 
23262346### Query parameters
23272347 
23282348- `version: optional number`
from line 2455
24352455 
24362456- `"anthropic-workspace-id": optional string`
24372457 
2458 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
2459 
2460 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
2461 
24382462### Returns
24392463 
24402464- `BetaManagedAgentsAgent object`
from line 3135
31113135 
31123136- `agent_id: string`
31133137 
3138 Unique identifier of the agent to update.
3139 
31143140### Headers
31153141 
31163142- `"anthropic-beta": optional array of AnthropicBeta`
from line 3241
32153241 
32163242- `"anthropic-workspace-id": optional string`
32173243 
3244 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
3245 
3246 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
3247 
32183248### Body parameters
32193249 
32203250- `description: optional string or null`
from line 3369
33393369 
33403370 - `"low"`
33413371 
3372 Low effort. Favors latency over reasoning depth.
3373 
33423374 - `"medium"`
33433375 
3376 Medium effort. Balances latency and reasoning depth.
3377 
33443378 - `"high"`
33453379 
3380 High effort. Favors reasoning depth.
3381 
33463382 - `"xhigh"`
33473383 
3384 Extra-high effort. Not all models accept this level.
3385 
33483386 - `"max"`
33493387 
3388 Maximum effort. Favors reasoning depth over latency.
3389 
33503390 - `BetaManagedAgentsEffortLow object`
33513391 
33523392 Low effort. Favors latency over reasoning depth.
from line 4647
46074647 
46084648- `agent_id: string`
46094649 
4650 Unique identifier of the agent to archive.
4651 
46104652### Headers
46114653 
46124654- `"anthropic-beta": optional array of AnthropicBeta`
from line 4753
47114753 
47124754- `"anthropic-workspace-id": optional string`
47134755 
4756 Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`).
4757 
4758 Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
4759 
47144760### Returns
47154761 
47164762- `BetaManagedAgentsAgent object`
from line 8338
82928338 
82938339 - `type: "max"`
82948340 
8295 - `inference_geo: optional string`
8296 
8297 Geographic region for model inference. When unset, requests fall through to the workspace's default_inference_geo.
8298 
8299 - `speed: optional "standard" or "fast"`
8300 
8301 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.
8302 
8303 - `"standard"`
8304 
8305 - `"fast"`
8306 
8307### Beta Managed Agents Model Config Params
8308 
8309- `BetaManagedAgentsModelConfigParams object`
8310 
8311 An object that defines additional configuration control over model use
8312 
8313 - `id: BetaManagedAgentsModel`
8314 
8315 The model that will power your agent.
8316 
8317 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
8318 
8319 - `"claude-fable-5-1" or "claude-sonnet-5" or "claude-fable-5" or 11 more`
8320 
8321 The model that will power your agent.
8322 
8323 See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
8324 
8325 - `"claude-fable-5-1"`
8326 
8327 Frontier intelligence for ambitious tasks across coding, scientific discovery, and enterprise workflows
8328 
8329 - `"claude-sonnet-5"`
8330 
8331 High-performance model for coding and agents
8332 
8333 - `"claude-fable-5"`
8334 
8335 Next generation of intelligence for the hardest knowledge work and coding problems
8336 
8337 - `"claude-opus-5"`
8338 
8339 Powerful intelligence for long-running agents and coding
8340 
8341 - `"claude-opus-4-8"`
8342 
8343 Powerful intelligence for long-running agents and coding
8344 
8345 - `"claude-opus-4-7"`
8346 
8347 Powerful intelligence for long-running agents and coding
8348 
8349 - `"claude-opus-4-6"`
8350 
8351 Powerful intelligence for long-running agents and coding
8352 
8353 - `"claude-sonnet-4-6"`
8354 
8355 Best combination of speed and intelligence
8356 
8357 - `"claude-haiku-4-5"`
8358 
8359 Fastest model with near-frontier intelligence
8360 
8361 - `"claude-haiku-4-5-20251001"`
8362 
8363 Fastest model with near-frontier intelligence
8364 
8365 - `"claude-opus-4-5"`
8366 
8367 Powerful intelligence for long-running agents and coding
8368 
8369 - `"claude-opus-4-5-20251101"`
8370 
8371 Powerful intelligence for long-running agents and coding
8372 
8373 - `"claude-sonnet-4-5"`
8374 
8375 High-performance model for agents and coding
8376 
8377 - `"claude-sonnet-4-5-20250929"`
8378 
8379 High-per
8341 - `inference_geo: optional str