Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.250 Feeds RSS JSON llms.txt

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

One change

Beta

api/beta

first seen The page's own history The capture it came from

Nearest release: v2.1.247, published under an hour before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

api/beta Changed · +12045 / -149 lines

## Beta › Organization ### Get Current Organization ## Beta › Organization › API Keys ### List API Keys ### Get API Key ### Update API Key ## Beta › Organization › External Keys ### Create External Key ### List External Keys ### Get External Key ### Update External Key ### Delete External Key ### Validate External Key ## Beta › Organization › Federation › Issuers ### Create Federation Issuer ### List Federation Issuers ### Get Federation Issuer ### Update Federation Issuer ### Archive Federation Issuer ## Beta › Organization › Federation › Rules ### Create Federation Rule ### List Federation Rules ### Get Federation Rule ### Update Federation Rule ### Archive Federation Rule ## Beta › Organization › Federation › Rules › Workspaces ### Add Federation Rule Workspace ### List Federation Rule Workspaces ### Remove Federation Rule Workspace ## Beta › Organization › Invites ### Create Invite ### List Invites ### Get Invite ### Delete Invite ## Beta › Organization › Service Accounts ### Create Service Account ### List Service Accounts ### Get Service Account ### Update Service Account ### Archive Service Account ## Beta › Organization › Service Accounts › Workspaces ### Add Workspace To Service Account ### List Workspaces For Service Account ### Remove Workspace From Service Account ## Beta › Organization › Users ### List Users ### Get User ### Update User ### Remove User ## Beta › Organization › Workspaces ### List Workspaces ### Create Workspace ### Get Workspace ### Update Workspace ### Archive Workspace ## Beta › Organization › Workspaces › Rate Limits ### List Workspace Rate Limits ## Beta › Organization › Workspaces › Members ### List Workspace Members ### Create Workspace Member ### Get Workspace Member ### Update Workspace Member ### Delete Workspace Member ## Beta › Organization › Workspaces › Service Accounts ### List Service Account Workspace Members ### Create Service Account Workspace Member ### Get Service Account Workspace Member ### Update Service Account Workspace Member ### Delete Service Account Workspace Member ## Beta › Organization › Rate Limits ### List Organization Rate Limits

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 4
 
 ### Anthropic Beta
 
-- `AnthropicBeta = string or "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+- `AnthropicBeta = string or "message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
   - `string`
 
-  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
     - `"message-batches-2024-09-24"`
 
from line 78
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
+    - `"compact-2026-01-12"`
+
+    - `"computer-use-2025-11-24"`
+
+    - `"mcp-tunnels-2026-06-22"`
+
+    - `"structured-outputs-2025-11-13"`
+
+    - `"task-budgets-2026-03-13"`
+
+    - `"thinking-display-updates-2026-08-18"`
+
+    - `"ce-user-management-2026-07-13"`
+
 ### Beta API Error
 
 - `BetaAPIError object`
from line 450
 
   - `string`
 
-  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
     - `"message-batches-2024-09-24"`
 
from line 520
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
+    - `"compact-2026-01-12"`
+
+    - `"computer-use-2025-11-24"`
+
+    - `"mcp-tunnels-2026-06-22"`
+
+    - `"structured-outputs-2025-11-13"`
+
+    - `"task-budgets-2026-03-13"`
+
+    - `"thinking-display-updates-2026-08-18"`
+
+    - `"ce-user-management-2026-07-13"`
+
 #### Returns
 
 - `data: array of BetaModelInfo`
from line 798
 
   - `string`
 
-  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
     - `"message-batches-2024-09-24"`
 
from line 868
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
+    - `"compact-2026-01-12"`
+
+    - `"computer-use-2025-11-24"`
+
+    - `"mcp-tunnels-2026-06-22"`
+
+    - `"structured-outputs-2025-11-13"`
+
+    - `"task-budgets-2026-03-13"`
+
+    - `"thinking-display-updates-2026-08-18"`
+
+    - `"ce-user-management-2026-07-13"`
+
 #### Returns
 
 - `BetaModelInfo object`
from line 1125
 
   - `string`
 
-  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
     - `"message-batches-2024-09-24"`
 
from line 1195
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
+    - `"compact-2026-01-12"`
+
+    - `"computer-use-2025-11-24"`
+
+    - `"mcp-tunnels-2026-06-22"`
+
+    - `"structured-outputs-2025-11-13"`
+
+    - `"task-budgets-2026-03-13"`
+
+    - `"thinking-display-updates-2026-08-18"`
+
+    - `"ce-user-management-2026-07-13"`
+
 - `"anthropic-user-profile-id": optional string`
 
   The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header.
from line 2889
 
         - `type: "enabled"`
 
-        - `display: optional "summarized" or "omitted" or null`
+        - `display: optional "summarized" or "omitted" or "updates" or null`
 
           Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
 
from line 2897
 
           - `"omitted"`
 
+          - `"updates"`
+
       - `BetaThinkingConfigDisabled object`
 
         - `type: "disabled"`
from line 2907
 
         - `type: "adaptive"`
 
-        - `display: optional "summarized" or "omitted" or null`
+        - `display: optional "summarized" or "omitted" or "updates" or null`
 
           Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
 
from line 2915
 
           - `"omitted"`
 
+          - `"updates"`
+
   - `Default = "default"`
 
 - `inference_geo: optional string or null`
from line 6427
 
       Per-iteration token usage breakdown.
 
-      Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:
+      Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to:
 
       - Determine which iterations exceeded long context thresholds (>=200k tokens)
-      - Calculate the true context window size from the last iteration
+      - Calculate the context window size from the last `message` entry
       - Understand token accumulation across server-side tool use loops
 
+      A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results.
+
       - `BetaMessageIterationUsage object`
 
         Token usage for a sampling iteration.
from line 6744
 
         Per-iteration token usage breakdown.
 
-        Each entry represents one sampling iteration, with its own input/output token counts and cache statistics. This allows you to:
+        Each entry represents one sampling iteration, with its own input/output token counts and cache statistics, discriminated by `type`. For `message` entries (model sampling iterations, such as the turns of a server-side tool use loop), this allows you to:
 
         - Determine which iterations exceeded long context thresholds (>=200k tokens)
-        - Calculate the true context window size from the last iteration
+        - Calculate the context window size from the last `message` entry
         - Understand token accumulation across server-side tool use loops
 
+        A `compaction` entry reports the token usage of the compaction operation itself — the server-side request that summarizes the context being closed — NOT the size of the context that was compacted away, and its token counts can be much smaller than that closed context (for example, a compaction that closes a ~200k-token context can report only a few thousand tokens). Do not derive the context window size from a `compaction` entry, even when it is the last entry. A `compaction` entry's tokens are not included in the top-level `usage` fields. When an input-token trigger is in effect (the default — 150,000 tokens unless configured otherwise), each `compaction` entry closes a context that had reached at least that threshold, though the context can exceed it by the final iteration's output and tool results.
+
       - `output_tokens: number`
 
         The cumulative number of output tokens which were used.
from line 7098
 
   - `string`
 
-  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 31 more`
+  - `"message-batches-2024-09-24" or "prompt-caching-2024-07-31" or "computer-use-2024-10-22" or 38 more`
 
     - `"message-batches-2024-09-24"`
 
from line 7168
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
+    - `"compact-2026-01-12"`
+
+    - `"computer-use-2025-11-24"`
+
+    - `"mcp-tunnels-2026-06-22"`
+
+    - `"structured-outputs-2025-11-13"`
+
+    - `"task-budgets-2026-03-13"`
+
+    - `"thinking-display-updates-2026-08-18"`
+
+    - `"ce-user-management-2026-07-13"`
+
 - `"anthropic-user-profile-id": optional string`
 
   The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization. Requires the `user-profiles` beta header.
from line 8786
 
     - `type: "enabled"`
 
-    - `display: optional "summarized" or "omitted" or null`
+    - `display: optional "summarized" or "omitted" or "updates" or null`
 
       Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
 
from line 8794
 
       - `"omitted"`
 
+      - `"updates"`
+
   - `BetaThinkingConfigDisabled object`
 
     - `type: "disabled"`
from line 8804
 
     - `type: "adaptive"`
 
-    - `display: optional "summarized" or "omitted" or null`
+    - `display: optional "summarized" or "omitted" or "updates" or null`
 
       Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
 
from line 8812
 
       - `"omitted"`
 
+      - `"updates"`
+
 - `tool_choice: optional BetaToolChoice`
 
   How the model should use the provided tools. The model can use a specific tool, any available tool, decide by itself, or not use tools at all.
from line 8870
 
   If you include `tools` in your API request, the model may return `tool_use` content blocks that represent the model's use of those tools. You can then run those tools using the tool input generated by the model and then optionally return results back to the model using `tool_result` content blocks.
 
-  There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool)).
-
-  Each tool definition includes:
-
-  * `name`: Name of the tool.
-  * `description`: Optional, but strongly-recommended description of the tool.
-  * `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the tool `input` shape that the model will produce in `tool_use` output content blocks.
-
-  For example, if you defined `tools` as:
-
-  ```json
-  [
-    {
-      "name": "get_stock_price",
-      "description": "Get the current stock price for a given ticker symbol.",
-      "input_schema": {
-        "type": "object",
-        "properties": {
-          "ticker": {
-            "type": "string",
-            "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
-          }
-        },
-        "required": ["ticker"]
-      }
-    }
-  ]
-  ```
-
-  And then asked the model "What's the S&P 500 at today?", the model might produce `tool_use` content blocks in the response like this:
-
-  ```json
-  [
-    {
-      "type": "tool_use",
-      "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
-      "name": "get_stock_price",
-      "input": { "ticker": "^GSPC" }
-    }
-  ]
-  ```
-
-  You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an input, and return the following back to the model in a subsequent `user` message:
-
-  ```json
-  [
-    {
-      "type": "tool_result",
-      "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
-      "content": "259.75 USD"
-    }
-  ]
-  ```
-
-  Tools can be used for workflows that include running client-side tools and functions, or more generally whenever you want the model to produce a particular JSON structure of output.
-
-  See our [guide](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) for more details.
-
-  - `BetaTool object`
-
-    - `input_schema: object`
-
-      [JSON schema](https://json-schema.org/draft/2020-12) for this tool's input.
-
-      This defines the shape of the `input` that your tool accepts and that the model will produce.
-
-      - `type: "object"`
-
-      - `properties: optional map[unknown] or null`
-
-      - `required: optional array of string or null`
-
-    - `name: string`
-
-      Name of the tool.
-
-      This is how the tool will be called by the model and in `tool_use` blocks.
-
-      maxLength: 128, minLength: 1, pattern: ^[a-zA-Z0-9_-]{1,128}$
-
-    - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
-
-      - `"direct"`
-
-      - `"code_execution_20250825"`
-
-      - `"code_execution_20260120"`
-
-      - `"code_execution_20260521"`
-
-    - `cache_control: optional BetaCacheControlEphemeral or null`
-
-      Create a cache control breakpoint at this content block.
-
-    - `defer_loading: optional boolean`
-
-      If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
-
-    - `description: optional string`
-
-      Description of what this tool does.
-
-      Tool descriptions should be as detailed as possible. The more information that the model has about what the tool is and how to use it, the better it will perform. You can use natural language descriptions to reinforce important aspects of the tool input JSON schema.
-
-    - `eager_input_streaming: optional boolean or null`
-
-      Enable eager inp
+  There are two types of tools: **client tools** and **server tools**. The behavior described below applies to client tools. For [server tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools), see their individual documentation as each has its own behavior (e.g., the [we