Messages changedapi/beta/messages
Nearest release: v2.1.306, 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.
Recorded here
Lines+340added
Lines−4removed
From line
131
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits29to this page, all time
The whole hunk
from line 131, old and new numbered
/
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 131
131131
132132 - `"telemetry-destinations-2026-08-11"`
133133
134 - `"webhooks-2026-10-07"`
135
134136- `"anthropic-user-profile-id": optional string`
135137
136138 The user profile ID to attribute this request to. Use when acting on behalf of a party other than your organization.
from line 3778
37763778
37773779 - `max_tokens: optional number or null`
37783780
3781 The `max_tokens` for the fallback attempt that uses this `fallbacks` entry's `model`, in place of the request's `max_tokens`. If you leave it out or set it to `null`, the attempt uses the request's `max_tokens`.
3782
3783 See the [refusals and fallback guide](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback?sdk_languages=http#naming-your-own-fallback-models) to learn more about fallback entries.
3784
37793785 - `output_config: optional BetaOutputConfig or null`
37803786
3787 Output parameters for the fallback attempt that uses this `fallbacks` entry's `model`, combined with the request's `output_config` one field at a time.
3788
3789 - `format`: If you leave it out, the attempt uses the request's `format`. If you set it to `null`, the attempt runs without a format.
3790 - `effort`: If you leave it out, the attempt uses the request's `effort` when `model` supports that level with the attempt's `thinking`. If the request doesn't set `effort`, if `model` doesn't support the level, or if you set `effort` to `null`, the attempt runs at the default effort of `model`.
3791 - `task_budget`: If you leave it out, the attempt uses the request's `task_budget` when `model` accepts a task budget of that size. If the request doesn't set `task_budget`, if `model` doesn't accept it, or if you set `task_budget` to `null`, the attempt runs without a task budget.
3792
3793 Set `output_config` to `null` to run the attempt without a format or a task budget, at the default effort of `model`.
3794
3795 These rules apply with the `server-side-fallback-2026-07-01` beta header.
3796
37813797 - `effort: optional "low" or "medium" or "high" or 2 more or null`
37823798
37833799 How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
from line 3842
38263842
38273843 - `speed: optional "standard" or "fast" or null`
38283844
3829 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.
3845 The inference speed mode for the fallback attempt that uses this `fallbacks` entry's `model`. If you leave it out, the attempt runs at `fast` speed only when the request sets `speed` to `fast` and your organization can use fast mode on `model`.
38303846
3847 Otherwise, or when you set this field to `null`, the attempt runs at `standard` speed.
3848
3849 These rules apply with the `server-side-fallback-2026-07-01` beta header.
3850
38313851 - `"standard"`
38323852
38333853 - `"fast"`
from line 3854
38343854
38353855 - `thinking: optional BetaThinkingConfigEnabled or BetaThinkingConfigDisabled or BetaThinkingConfigBetweenTools or BetaThinkingConfigAdaptive or null`
38363856
3857 The thinking configuration for the fallback attempt that uses this `fallbacks` entry's `model`. If you leave it out, the attempt uses the request's `thinking` when `model` supports that thinking `type`.
3858
3859 If you leave it out and the request's thinking `type` is `between_tools` but `model` doesn't support `between_tools`, the attempt uses `disabled` if `model` supports it. Otherwise, if `model` doesn't support the request's thinking `type`, if the request doesn't set `thinking`, or if you set this field to `null`, the attempt uses the thinking `type` that `model` uses when a request leaves out `thinking`. The request's `thinking.display` still applies where `model` allows it.
3860
3861 These rules apply with the `server-side-fallback-2026-07-01` beta header.
3862
38373863 - `BetaThinkingConfigEnabled object`
38383864
38393865 - `type: "enabled"`
from line 7122
70967122
70977123 - `max_tokens: optional number or null`
70987124
7099 Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the returned advisor_result or advisor_redacted_result block carries stop_reason='max_tokens', and a truncation note is appended to the advice text the worker model sees (inside the encrypted blob in redacted mode). When set, the server also emits a remaining-tokens budget block in the advisor's prompt so the advisor self-shapes toward the cap. When omitted, the advisor model's default output cap applies and no budget block is emitted.
7100
7101 minimum: 1024
7102
7103 - `max_uses: optional number or null`
7104
7105 Maximum number of times the tool can be used in the API request.
7106
7107 minimum: 1
7108
7109 - `strict: optional boolean`
7110
7111 When true, guarantees schema validation on tool names and inputs
7112
7113 - `BetaToolSearchToolBm25_20251119 object`
7114
7115 - `type: "tool_search_tool_bm25_20251119" or "tool_search_tool_bm25"`
7116
7117 - `"tool_search_tool_bm25_20251119"`
7118
7119 - `"tool_search_tool_bm25"`
7120
7121 - `name: "tool_search_tool_bm25"`
7122
7123 Name of the tool.
7124
7125 This is how the tool will be called by the model and in `tool_use` blocks.
7126
7127 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`
7128
7129 - `"direct"`
7130
7131 - `"code_execution_20250825"`
7132
7133 - `"code_execution_20260120"`
7134
7135 - `"code_execution_20260521"`
7136
7137 - `cache_control: optional BetaCacheControlEphemeral or null`
7138
7139 Create a cache control breakpoint at this content block.
7140
7141 - `defer_loading: optional boolean`
7142
7143 If true, tool will not be included in initial system prompt. Only loaded when returned via tool_reference from tool search.
7144
7145 - `strict: optional boolean`
7146
7147 When true, guarantees schema validation on tool names and inputs
7148
7149 - `BetaToolSearchToolRegex20251119 object`
7150
7151 - `type: "tool_search_tool_regex_20251119" or "tool_search_tool_regex"`
7152
7153 - `"tool_search_tool_regex_20251119"`
7154
7155 - `"tool_search_tool_regex"`
7156
7157 - `name: "tool_search_tool_regex"`
7158
7159 Name of the tool.
7160
7161 This is how the tool will be called by the model and in `tool_use` blocks.
7162
7163 - `allowed_callers: optional array of "direct" or
7125 Bounds the advisor's total output (thinking + text) per call. When the advisor hits this cap, the retur
No line in this hunk matches that.