Messages
Create a Message
$ ant messages createSend a structured list of input messages with text and/or image content, and the model will generate the next message in the conversation.
Count tokens in a Message
$ ant messages count-tokensCount the number of tokens in a Message.
Models
base64_image_source: object{ type: "base64", data, media_type }
data: string
media_type: "image/jpeg" or "image/png" or "image/gif" or "image/webp"
base64_pdf_source: object{ type: "base64", data, media_type }
data: string
bash_code_execution_output_block: object{ type: "bash_code_execution_output", file_id }
bash_code_execution_output_block_param: object{ type: "bash_code_execution_output", file_id }
bash_code_execution_result_block: object{ type: "bash_code_execution_result", content, return_code, 2 more }
content: array of BashCodeExecutionOutputBlock { type: "bash_code_execution_output", file_id }
bash_code_execution_result_block_param: object{ type: "bash_code_execution_result", content, return_code, 2 more }
content: array of BashCodeExecutionOutputBlockParam { type: "bash_code_execution_output", file_id }
bash_code_execution_tool_result_block: object{ type: "bash_code_execution_tool_result", content, tool_use_id }
bash_code_execution_tool_result_block_param: object{ type: "bash_code_execution_tool_result", content, tool_use_id, cache_control }
bash_code_execution_tool_result_error: object{ type: "bash_code_execution_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
bash_code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
bash_code_execution_tool_result_error_param: object{ type: "bash_code_execution_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
browser_click_target: BrowserCoordinateTarget or BrowserRefTargetWhere to act: either a viewport coordinate or an element reference.
Where to act: either a viewport coordinate or an element reference.
browser_coordinate_target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
browser_ref_target: object{ type: "ref", ref }An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element reference (e.g. "ref_7") returned by a prior read_page or find result.
browser_close_tab_config: object{ defer_loading, enabled }close_tab's config overrides.
close_tab's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_close_tab_input: object{ tab_id }Close the tab with the given tab_id.
Close the tab with the given tab_id.
The tab to close.
browser_close_tab_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_coordinate_target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
browser_double_click_config: object{ defer_loading, enabled }double_click's config overrides.
double_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_double_click_input: object{ target, modifiers, tab_id }Double left-click at a viewport coordinate or on an element by reference.
Double left-click at a viewport coordinate or on an element by reference.
browser_double_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_file_upload_config: object{ defer_loading, enabled }file_upload's config overrides.
file_upload's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_file_upload_input: object{ target, document_ids, paths, tab_id }Set the value of a file-input element to one or more files. The target must be an
element reference; at least one of paths or document_ids is required.
Set the value of a file-input element to one or more files. The target must be an element reference; at least one of paths or document_ids is required.
target: object{ type: "ref", ref }An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element reference (e.g. "ref_7") returned by a prior read_page or find result.
document_ids: optional array of stringReferences to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem.
References to files the harness has staged, for deployments where the browser executor cannot read the caller's filesystem.
paths: optional array of stringFile paths on the browser executor's filesystem.
File paths on the browser executor's filesystem.
Tab to act on. Defaults to the active tab when omitted.
browser_file_upload_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_find_config: object{ defer_loading, enabled }find's config overrides.
find's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_find_input: object{ query, tab_id }Find elements matching a natural-language description (e.g. "search bar", "add to
cart button") and return up to 20 matches with element references.
Find elements matching a natural-language description (e.g. "search bar", "add to cart button") and return up to 20 matches with element references.
Natural-language description of the element(s) to find.
Tab to act on. Defaults to the active tab when omitted.
browser_find_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_form_input_config: object{ defer_loading, enabled }form_input's config overrides.
form_input's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_form_input_input: object{ target, value, tab_id }Set the value of a form element (input, textarea, select, checkbox). Use a
boolean for checkboxes, an option value or text for selects.
Set the value of a form element (input, textarea, select, checkbox). Use a boolean for checkboxes, an option value or text for selects.
target: object{ type: "ref", ref }An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element reference (e.g. "ref_7") returned by a prior read_page or find result.
value: string or number or booleanThe value to set.
The value to set.
Tab to act on. Defaults to the active tab when omitted.
browser_form_input_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_form_input_value: string or number or boolean
browser_get_page_text_config: object{ defer_loading, enabled }get_page_text's config overrides.
get_page_text's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_get_page_text_input: object{ tab_id }Return the page's visible text content as plain text, prioritizing article
content. Suited to articles, documentation, and other text-heavy pages.
Return the page's visible text content as plain text, prioritizing article content. Suited to articles, documentation, and other text-heavy pages.
Tab to act on. Defaults to the active tab when omitted.
browser_get_page_text_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_hold_key_config: object{ defer_loading, enabled }hold_key's config overrides.
hold_key's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_hold_key_input: object{ duration, text, tab_id }Hold a key or key chord down for a duration, then release it. Uses the same key
names and "+" chord syntax as the key action.
Hold a key or key chord down for a duration, then release it. Uses the same key names and "+" chord syntax as the key action.
duration: numberSeconds to hold the key down (maximum 30).
Seconds to hold the key down (maximum 30).
The key or chord to hold.
Tab to act on. Defaults to the active tab when omitted.
browser_hold_key_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_hover_config: object{ defer_loading, enabled }hover's config overrides.
hover's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_hover_input: object{ target, tab_id }Move the cursor to a coordinate or element without clicking.
Move the cursor to a coordinate or element without clicking.
browser_hover_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_javascript_exec_config: object{ defer_loading, enabled }javascript_exec's config overrides.
javascript_exec's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_javascript_exec_input: object{ text, tab_id }Execute JavaScript in the page context and return the value of the last
expression. The code runs with access to the DOM, window, and page variables.
Write the expression you want evaluated — do NOT use return.
Execute JavaScript in the page context and return the value of the last
expression. The code runs with access to the DOM, window, and page variables.
Write the expression you want evaluated — do NOT use return.
JavaScript to execute in the page context.
Tab to act on. Defaults to the active tab when omitted.
browser_javascript_exec_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_key_config: object{ defer_loading, enabled }key's config overrides.
key's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_key_input: object{ text, repeat, tab_id }Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a",
"cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete").
Common names like "Return", "Tab", "Escape", "BackSpace" are supported.
Press a key or key chord. Use "+" to combine modifiers with a key (e.g. "ctrl+a", "cmd+shift+p") and space to sequence presses (e.g. "Backspace Backspace Delete"). Common names like "Return", "Tab", "Escape", "BackSpace" are supported.
The key, chord, or space-separated sequence to press.
repeat: optional numberNumber of times to repeat. Default 1.
Number of times to repeat. Default 1.
Tab to act on. Defaults to the active tab when omitted.
browser_key_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_left_click_config: object{ defer_loading, enabled }left_click's config overrides.
left_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_left_click_drag_config: object{ defer_loading, enabled }left_click_drag's config overrides.
left_click_drag's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_left_click_drag_input: object{ from, target, tab_id }Press at from, drag to target, release. Both must be coordinate targets.
Press at from, drag to target, release. Both must be coordinate targets.
browser_left_click_drag_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_left_click_input: object{ target, modifiers, tab_id }Left-click at a viewport coordinate or on an element by reference.
Left-click at a viewport coordinate or on an element by reference.
browser_left_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_left_mouse_down_config: object{ defer_loading, enabled }left_mouse_down's config overrides.
left_mouse_down's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_left_mouse_down_input: object{ target, tab_id }Press and hold the left mouse button at a viewport coordinate. Pair with
left_mouse_up to perform a custom drag.
Press and hold the left mouse button at a viewport coordinate. Pair with left_mouse_up to perform a custom drag.
target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
Tab to act on. Defaults to the active tab when omitted.
browser_left_mouse_down_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_left_mouse_up_config: object{ defer_loading, enabled }left_mouse_up's config overrides.
left_mouse_up's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_left_mouse_up_input: object{ target, tab_id }Release the left mouse button at a viewport coordinate.
Release the left mouse button at a viewport coordinate.
target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
Tab to act on. Defaults to the active tab when omitted.
browser_left_mouse_up_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_list_tabs_config: object{ defer_loading, enabled }list_tabs's config overrides.
list_tabs's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
List all open tabs with each tab's tab_id, title, and URL.
browser_list_tabs_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_middle_click_config: object{ defer_loading, enabled }middle_click's config overrides.
middle_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_middle_click_input: object{ target, modifiers, tab_id }Middle-click at a viewport coordinate or on an element by reference.
Middle-click at a viewport coordinate or on an element by reference.
browser_middle_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_mouse_move_config: object{ defer_loading, enabled }mouse_move's config overrides.
mouse_move's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_mouse_move_input: object{ target, tab_id }Move the pointer to a viewport coordinate without clicking.
Move the pointer to a viewport coordinate without clicking.
target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
Tab to act on. Defaults to the active tab when omitted.
browser_mouse_move_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_navigate_config: object{ defer_loading, enabled }navigate's config overrides.
navigate's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_navigate_input: object{ url, tab_id }Navigate to a URL, or go back/forward/reload in history. The protocol may be
omitted (defaults to https://).
Navigate to a URL, or go back/forward/reload in history. The protocol may be omitted (defaults to https://).
The URL to navigate to, or "back" / "forward" / "reload" for history navigation.
Tab to act on. Defaults to the active tab when omitted.
browser_navigate_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_new_tab_config: object{ defer_loading, enabled }new_tab's config overrides.
new_tab's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
Open a new empty tab and return its tab_id.
browser_new_tab_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_read_console_config: object{ defer_loading, enabled }read_console's config overrides.
read_console's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_read_console_input: object{ tab_id }Return console output (log entries, errors, warnings) accumulated since the
driver attached to the tab and since the last read, one line per entry. An empty
result does not mean no traffic for a tab that predates attach.
Return console output (log entries, errors, warnings) accumulated since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach.
Tab to act on. Defaults to the active tab when omitted.
browser_read_console_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_read_network_config: object{ defer_loading, enabled }read_network's config overrides.
read_network's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_read_network_input: object{ tab_id }Return the network requests (method, URL, status, MIME type, timing) recorded
since the driver attached to the tab and since the last read, one line per entry.
An empty result does not mean no traffic for a tab that predates attach.
Return the network requests (method, URL, status, MIME type, timing) recorded since the driver attached to the tab and since the last read, one line per entry. An empty result does not mean no traffic for a tab that predates attach.
Tab to act on. Defaults to the active tab when omitted.
browser_read_network_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_read_page_config: object{ defer_loading, enabled }read_page's config overrides.
read_page's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_read_page_filter: "all" or "interactive"
browser_read_page_input: object{ depth, filter, ref, tab_id }Return a structured accessibility tree of the page (or the subtree rooted at
ref), with element references like [ref_7] that can be used as targets on later
actions. Output is capped at 50,000 characters — narrow with ref or a smaller
depth when exceeded.
Return a structured accessibility tree of the page (or the subtree rooted at
ref), with element references like [ref_7] that can be used as targets on later
actions. Output is capped at 50,000 characters — narrow with ref or a smaller
depth when exceeded.
depth: optional numberMaximum tree depth. Default 15.
Maximum tree depth. Default 15.
filter: optional "all" or "interactive"Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements.
Which elements to include. Omitted: every visible element. "interactive": interactive elements only. "all": additionally includes off-viewport elements.
Element reference to read a subtree from. Omit to read from the page root.
Tab to act on. Defaults to the active tab when omitted.
browser_read_page_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_ref_target: object{ type: "ref", ref }An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element reference (e.g. "ref_7") returned by a prior read_page or find result.
browser_right_click_config: object{ defer_loading, enabled }right_click's config overrides.
right_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_right_click_input: object{ target, modifiers, tab_id }Right-click at a viewport coordinate or on an element by reference.
Right-click at a viewport coordinate or on an element by reference.
browser_right_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_screenshot_config: object{ defer_loading, enabled }screenshot's config overrides.
screenshot's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_screenshot_input: object{ tab_id }Capture the current browser viewport.
Capture the current browser viewport.
Tab to act on. Defaults to the active tab when omitted.
browser_screenshot_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_scroll_config: object{ defer_loading, enabled }scroll's config overrides.
scroll's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_scroll_direction: "up" or "down" or "left" or "right"
browser_scroll_input: object{ scroll_direction, target, scroll_amount, tab_id }Scroll at a viewport position. target must be a coordinate target.
Scroll at a viewport position. target must be a coordinate target.
scroll_direction: "up" or "down" or "left" or "right"
target: object{ type: "coordinate", x, y }A point in the browser viewport, in viewport pixels (the same frame as a
full-viewport screenshot).
A point in the browser viewport, in viewport pixels (the same frame as a full-viewport screenshot).
x: numberPixels from the left edge of the viewport.
Pixels from the left edge of the viewport.
y: numberPixels from the top edge of the viewport.
Pixels from the top edge of the viewport.
scroll_amount: optional numberScroll-wheel notches (1–10). Default 3.
Scroll-wheel notches (1–10). Default 3.
Tab to act on. Defaults to the active tab when omitted.
browser_scroll_to_config: object{ defer_loading, enabled }scroll_to's config overrides.
scroll_to's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_scroll_to_input: object{ target, tab_id }Scroll an element into view.
Scroll an element into view.
target: object{ type: "ref", ref }An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element on the page, identified by a reference from a prior read_page or
find result. References are scoped to the tab that produced them and become
stale after navigation or a major re-render.
An element reference (e.g. "ref_7") returned by a prior read_page or find result.
Tab to act on. Defaults to the active tab when omitted.
browser_scroll_to_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_scroll_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_state_block_param: object{ type: "browser_state", tabs, cache_control, state_changes }The caller's browser state after a browser toolset member call —
the full inventory of open tabs, which tab is active, and any side
effects (tabs opened, download state changes) the call produced.
The caller's browser state after a browser toolset member call — the full inventory of open tabs, which tab is active, and any side effects (tabs opened, download state changes) the call produced.
At most one per tool_result, only on a non-error result answering a
browser toolset member tool_use. The server renders the
model-visible text from it; the model never sees the raw fields.
browser_state_change: BrowserStateChangeTabOpened or BrowserStateChangeDownloadStarted or BrowserStateChangeDownloadCompleted or BrowserStateChangeDownloadFailed
browser_state_change_download_completed: object{ type: "download_completed", download_id, url, 2 more }A file download that finished during this call, reported with the
same download_id as its download_started — or without a prior
download_started, when the download finished during the call that
started it (at most one state change per download_id per result).
A file download that finished during this call, reported with the
same download_id as its download_started — or without a prior
download_started, when the download finished during the call that
started it (at most one state change per download_id per result).
download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
The caller-assigned identifier for this download, stable across the state changes reporting it.
url: stringThe final post-redirect URL the download was served from.
The final post-redirect URL the download was served from.
path: optional stringWhere the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
Where the executor saved the file, on the executor's filesystem. Only included when another tool in the same environment can read the file at that path.
size_bytes: optional numberThe completed download's size.
The completed download's size.
browser_state_change_download_failed: object{ type: "download_failed", download_id, url, error }A file download that failed — or was cancelled — during this call.
A file download that failed — or was cancelled — during this call.
download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
The caller-assigned identifier for this download, stable across the state changes reporting it.
url: stringThe final post-redirect URL the download was served from.
The final post-redirect URL the download was served from.
error: optional stringThe failure or cancellation detail, when known.
The failure or cancellation detail, when known.
browser_state_change_download_started: object{ type: "download_started", download_id, url }A file download that started during this call.
A file download that started during this call.
download_id: stringThe caller-assigned identifier for this download, stable across the state changes reporting it.
The caller-assigned identifier for this download, stable across the state changes reporting it.
url: stringThe final post-redirect URL the download was served from.
The final post-redirect URL the download was served from.
browser_state_change_tab_opened: object{ type: "tab_opened", tab_id }A tab this call's execution opened that remains open at its end —
the creation delta of the tabs inventory, not an event log.
A tab this call's execution opened that remains open at its end —
the creation delta of the tabs inventory, not an event log.
Carries only the tab_id; the tab's title and url live on its
tabs entry, which must include the same tab_id. A tab opened
during a failed call gets no deferred tab_opened; it simply appears
in the next result's tabs inventory.
tab_id: stringThe tab_id of the opened tab, present in tabs.
The tab_id of the opened tab, present in tabs.
browser_state_tab_entry: object{ tab_id, title, url, active }One open browser tab reported in a browser_state block's tabs
inventory.
One open browser tab reported in a browser_state block's tabs
inventory.
tab_id is the caller-assigned identifier for the tab; title and
url describe the page the tab is currently showing and may be empty
strings (a blank tab legitimately has both empty). active marks the
tab that is active after this call; whenever tabs is non-empty,
exactly one entry is marked.
tab_id: stringThe caller-assigned identifier for this tab, unique within the inventory.
The caller-assigned identifier for this tab, unique within the inventory.
title: stringThe title of the page the tab is showing. May be empty.
The title of the page the tab is showing. May be empty.
url: stringThe URL of the page the tab is showing. May be empty.
The URL of the page the tab is showing. May be empty.
Whether this tab is the active tab after this call. Whenever tabs is non-empty, exactly one entry is marked active: true.
browser_switch_tab_config: object{ defer_loading, enabled }switch_tab's config overrides.
switch_tab's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_switch_tab_input: object{ tab_id }Make the tab with the given tab_id the active tab — the tab that actions without
a tab_id apply to.
Make the tab with the given tab_id the active tab — the tab that actions without a tab_id apply to.
The tab to switch to.
browser_switch_tab_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_tool_use_block: BrowserNavigateToolUseBlock or BrowserListTabsToolUseBlock or BrowserNewTabToolUseBlock or 28 more
browser_toolset_20260801: object{ type: "browser_toolset_20260801", cache_control, configs }The browser toolset: a single tools[] entry (carrying no
name) that declares the browser tool family. The model is served
the family's tool with any members disabled via configs removed
from its schema.
The browser toolset: a single tools[] entry (carrying no
name) that declares the browser tool family. The model is served
the family's tool with any members disabled via configs removed
from its schema.
browser_toolset_configs: object{ type, close_tab, double_click, 28 more }Per-member configuration for browser_toolset_20260801: one
optional field per member tool, keyed by the member name — the same
name the member's tool_use blocks carry. Every member is an
accepted key, and a member's defaults apply wherever its key is
absent. Unknown keys are rejected: the field set is this toolset
version's complete member set.
Per-member configuration for browser_toolset_20260801: one
optional field per member tool, keyed by the member name — the same
name the member's tool_use blocks carry. Every member is an
accepted key, and a member's defaults apply wherever its key is
absent. Unknown keys are rejected: the field set is this toolset
version's complete member set.
browser_triple_click_config: object{ defer_loading, enabled }triple_click's config overrides.
triple_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_triple_click_input: object{ target, modifiers, tab_id }Triple left-click at a viewport coordinate or on an element by reference
(typically selects a line or paragraph).
Triple left-click at a viewport coordinate or on an element by reference (typically selects a line or paragraph).
browser_triple_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_type_config: object{ defer_loading, enabled }type's config overrides.
type's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_type_input: object{ text, tab_id }Type a literal string at the current focus.
Type a literal string at the current focus.
The text to type.
Tab to act on. Defaults to the active tab when omitted.
browser_type_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_wait_config: object{ defer_loading, enabled }wait's config overrides.
wait's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_wait_input: object{ duration, tab_id }Pause for the given duration.
Pause for the given duration.
duration: numberSeconds to wait (maximum 30).
Seconds to wait (maximum 30).
Tab to act on. Defaults to the active tab when omitted.
browser_wait_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
browser_zoom_config: object{ defer_loading, enabled }zoom's config overrides.
zoom's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
browser_zoom_input: object{ region, tab_id }Return a cropped screenshot of the given viewport region, scaled up for closer
inspection — useful for small icons, buttons, or text. Coordinates are in the
same viewport-pixel space as a full screenshot.
Return a cropped screenshot of the given viewport region, scaled up for closer inspection — useful for small icons, buttons, or text. Coordinates are in the same viewport-pixel space as a full screenshot.
region: array of number[x0, y0, x1, y1] in viewport pixels.
[x0, y0, x1, y1] in viewport pixels.
Tab to act on. Defaults to the active tab when omitted.
browser_zoom_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
cache_control_ephemeral: object{ type: "ephemeral", ttl }
ttl: optional "5m" or "1h"The time-to-live for the cache control breakpoint.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m. See prompt caching pricing for details.
cache_creation: object{ ephemeral_1h_input_tokens, ephemeral_5m_input_tokens }
ephemeral_1h_input_tokens: numberThe number of input tokens used to create the 1 hour cache entry.
The number of input tokens used to create the 1 hour cache entry.
ephemeral_5m_input_tokens: numberThe number of input tokens used to create the 5 minute cache entry.
The number of input tokens used to create the 5 minute cache entry.
cache_miss_messages_changed: object{ type: "messages_changed", cache_missed_input_tokens }
Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
cache_miss_model_changed: object{ type: "model_changed", cache_missed_input_tokens }
Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
cache_miss_previous_message_not_found: object{ type: "previous_message_not_found" }
cache_miss_reason: CacheMissModelChanged or CacheMissSystemChanged or CacheMissToolsChanged or 3 more
cache_miss_system_changed: object{ type: "system_changed", cache_missed_input_tokens }
Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
cache_miss_tools_changed: object{ type: "tools_changed", cache_missed_input_tokens }
Approximate number of input tokens that would have been read from cache had the prefix matched the previous request.
cache_miss_unavailable: object{ type: "unavailable" }
citation_char_location: object{ type: "char_location", cited_text, document_index, 4 more }
document_index: number
start_char_index: number
citation_char_location_param: object{ type: "char_location", cited_text, document_index, 3 more }
document_index: number
document_title: string
start_char_index: number
citation_content_block_location: object{ type: "content_block_location", cited_text, document_index, 4 more }
cited_text: stringThe full text of the cited block range, concatenated.
The full text of the cited block range, concatenated.
Always equals the contents of content[start_block_index:end_block_index] joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.
document_index: number
end_block_index: numberExclusive 0-based end index of the cited block range in the source's content array.
Exclusive 0-based end index of the cited block range in the source's content array.
Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.
start_block_index: number0-based index of the first cited block in the source's content array.
0-based index of the first cited block in the source's content array.
citation_content_block_location_param: object{ type: "content_block_location", cited_text, document_index, 3 more }
cited_text: stringThe full text of the cited block range, concatenated.
The full text of the cited block range, concatenated.
Always equals the contents of content[start_block_index:end_block_index] joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.
document_index: number
document_title: string
end_block_index: numberExclusive 0-based end index of the cited block range in the source's content array.
Exclusive 0-based end index of the cited block range in the source's content array.
Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.
start_block_index: number0-based index of the first cited block in the source's content array.
0-based index of the first cited block in the source's content array.
citation_page_location: object{ type: "page_location", cited_text, document_index, 4 more }
document_index: number
start_page_number: number
citation_page_location_param: object{ type: "page_location", cited_text, document_index, 3 more }
document_index: number
document_title: string
start_page_number: number
citation_search_result_location_param: object{ type: "search_result_location", cited_text, end_block_index, 4 more }
cited_text: stringThe full text of the cited block range, concatenated.
The full text of the cited block range, concatenated.
Always equals the contents of content[start_block_index:end_block_index] joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.
end_block_index: numberExclusive 0-based end index of the cited block range in the source's content array.
Exclusive 0-based end index of the cited block range in the source's content array.
Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.
search_result_index: number0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.
0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.
Counted separately from document_index; server-side web search results are not included in this count.
start_block_index: number0-based index of the first cited block in the source's content array.
0-based index of the first cited block in the source's content array.
citation_web_search_result_location_param: object{ type: "web_search_result_location", cited_text, encrypted_index, 2 more }
title: string
url: string
citations_config: object{ enabled }
citations_config_param: object{ enabled }
citations_delta: object{ type: "citations_delta", citation }
citations_search_result_location: object{ type: "search_result_location", cited_text, end_block_index, 4 more }
cited_text: stringThe full text of the cited block range, concatenated.
The full text of the cited block range, concatenated.
Always equals the contents of content[start_block_index:end_block_index] joined together. The text block is the minimal citable unit; this field is never a substring of a single block. Not counted toward output tokens, and not counted toward input tokens when sent back in subsequent turns.
end_block_index: numberExclusive 0-based end index of the cited block range in the source's content array.
Exclusive 0-based end index of the cited block range in the source's content array.
Always greater than start_block_index; a single-block citation has end_block_index = start_block_index + 1.
search_result_index: number0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.
0-based index of the cited search result among all search_result content blocks in the request, in the order they appear across messages and tool results.
Counted separately from document_index; server-side web search results are not included in this count.
start_block_index: number0-based index of the first cited block in the source's content array.
0-based index of the first cited block in the source's content array.
citations_web_search_result_location: object{ type: "web_search_result_location", cited_text, encrypted_index, 2 more }
title: string
code_execution_output_block: object{ type: "code_execution_output", file_id }
code_execution_output_block_param: object{ type: "code_execution_output", file_id }
code_execution_result_block: object{ type: "code_execution_result", content, return_code, 2 more }
content: array of CodeExecutionOutputBlock { type: "code_execution_output", file_id }
code_execution_result_block_param: object{ type: "code_execution_result", content, return_code, 2 more }
content: array of CodeExecutionOutputBlockParam { type: "code_execution_output", file_id }
code_execution_tool_20250522: object{ type: "code_execution_20250522", name, allowed_callers, 3 more }
code_execution_tool_20250825: object{ type: "code_execution_20250825", name, allowed_callers, 3 more }
code_execution_tool_20260120: object{ type: "code_execution_20260120", name, allowed_callers, 3 more }Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
Code execution tool with REPL state persistence (daemon mode + gVisor checkpoint).
code_execution_tool_20260521: object{ type: "code_execution_20260521", name, allowed_callers, 3 more }Code execution tool with REPL state persistence.
Code execution tool with REPL state persistence.
code_execution_tool_result_block: object{ type: "code_execution_tool_result", content, tool_use_id }
code_execution_tool_result_block_content: CodeExecutionToolResultError or CodeExecutionResultBlock or EncryptedCodeExecutionResultBlock
code_execution_tool_result_block_param: object{ type: "code_execution_tool_result", content, tool_use_id, cache_control }
code_execution_tool_result_block_param_content: CodeExecutionToolResultErrorParam or CodeExecutionResultBlockParam or EncryptedCodeExecutionResultBlockParam
code_execution_tool_result_error: object{ type: "code_execution_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
code_execution_tool_result_error_param: object{ type: "code_execution_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
computer_cursor_position_config: object{ defer_loading, enabled }cursor_position's config overrides.
cursor_position's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
Get the current (x, y) pixel coordinate of the cursor.
computer_cursor_position_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_double_click_config: object{ defer_loading, enabled }double_click's config overrides.
double_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_double_click_input: object{ coordinate, text }Double-click the left mouse button at the specified (x, y) pixel coordinate, or
the current cursor position if coordinate is omitted.
Double-click the left mouse button at the specified (x, y) pixel coordinate, or
the current cursor position if coordinate is omitted.
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_double_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_hold_key_config: object{ defer_loading, enabled }hold_key's config overrides.
hold_key's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_hold_key_input: object{ duration, text }Hold down a key or key-combination for a specified duration. Uses the same key
syntax as key.
Hold down a key or key-combination for a specified duration. Uses the same key
syntax as key.
duration: numberDuration to hold the key, in seconds.
Duration to hold the key, in seconds.
The key or key-combination to hold.
computer_hold_key_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_key_config: object{ defer_loading, enabled }key's config overrides.
key's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_key_input: object{ text, repeat }Press a key or key-combination on the keyboard. Use "+" to combine modifiers with
a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are
case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down",
"Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are
supported.
Press a key or key-combination on the keyboard. Use "+" to combine modifiers with a key (e.g. "ctrl+s", "alt+Tab", "ctrl+shift+Escape"). Key names are case-insensitive; common names like "Return", "Tab", "Escape", "Up", "Down", "Left", "Right", "Home", "End", "Page_Up", "Page_Down", "Delete", "BackSpace" are supported.
The key or key-combination to press.
repeat: optional numberNumber of times to repeat the key press. Default is 1.
Number of times to repeat the key press. Default is 1.
computer_key_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_left_click_config: object{ defer_loading, enabled }left_click's config overrides.
left_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_left_click_drag_config: object{ defer_loading, enabled }left_click_drag's config overrides.
left_click_drag's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_left_click_drag_input: object{ coordinate, start_coordinate, text }Click and drag the cursor from start_coordinate to coordinate.
Click and drag the cursor from start_coordinate to coordinate.
coordinate: array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
start_coordinate: array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_left_click_drag_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_left_click_input: object{ coordinate, text }Click the left mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
Click the left mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_left_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_left_mouse_down_config: object{ defer_loading, enabled }left_mouse_down's config overrides.
left_mouse_down's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
Press and hold the left mouse button at the current cursor position.
computer_left_mouse_down_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_left_mouse_up_config: object{ defer_loading, enabled }left_mouse_up's config overrides.
left_mouse_up's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
Release the left mouse button.
computer_left_mouse_up_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_middle_click_config: object{ defer_loading, enabled }middle_click's config overrides.
middle_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_middle_click_input: object{ coordinate, text }Click the middle mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
Click the middle mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_middle_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_mouse_move_config: object{ defer_loading, enabled }mouse_move's config overrides.
mouse_move's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_mouse_move_input: object{ coordinate }Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover
without clicking; otherwise use a click action directly.
Move the cursor to a specified (x, y) pixel coordinate. Use this ONLY to hover without clicking; otherwise use a click action directly.
coordinate: array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
computer_mouse_move_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_right_click_config: object{ defer_loading, enabled }right_click's config overrides.
right_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_right_click_input: object{ coordinate, text }Click the right mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
Click the right mouse button at the specified (x, y) pixel coordinate, or the
current cursor position if coordinate is omitted.
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_right_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_screenshot_config: object{ defer_loading, enabled }screenshot's config overrides.
screenshot's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
Take a screenshot of the screen.
computer_screenshot_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_scroll_config: object{ defer_loading, enabled }scroll's config overrides.
scroll's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_scroll_direction: "up" or "down" or "left" or "right"
computer_scroll_input: object{ scroll_amount, scroll_direction, coordinate, text }Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor
position if coordinate is omitted. Do NOT use PageUp/PageDown to scroll.
Scroll the screen at the specified (x, y) pixel coordinate, or the current cursor
position if coordinate is omitted. Do NOT use PageUp/PageDown to scroll.
Number of 'clicks' of the scroll wheel.
scroll_direction: "up" or "down" or "left" or "right"
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_scroll_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_tool_use_block: ComputerKeyToolUseBlock or ComputerHoldKeyToolUseBlock or ComputerTypeToolUseBlock or 14 more
computer_toolset_20260801: object{ type: "computer_toolset_20260801", cache_control, configs }The computer toolset: a single tools[] entry (carrying no
name) that declares the computer tool family. The model is
served the family's tool with any members disabled via configs
removed from its schema. Every member is enabled by default, zoom
included. The single-tool options display_number and
enable_zoom are not fields of a toolset entry — it carries only
type, configs, and cache_control; zoom is controlled
via configs.zoom.enabled.
The computer toolset: a single tools[] entry (carrying no
name) that declares the computer tool family. The model is
served the family's tool with any members disabled via configs
removed from its schema. Every member is enabled by default, zoom
included. The single-tool options display_number and
enable_zoom are not fields of a toolset entry — it carries only
type, configs, and cache_control; zoom is controlled
via configs.zoom.enabled.
computer_toolset_configs: object{ type, cursor_position, double_click, 14 more }Per-member configuration for computer_toolset_20260801: one
optional field per member tool, keyed by the member name — the same
name the member's tool_use blocks carry. Every member is an
accepted key, and a member's defaults apply wherever its key is
absent. Unknown keys are rejected: the field set is this toolset
version's complete member set.
Per-member configuration for computer_toolset_20260801: one
optional field per member tool, keyed by the member name — the same
name the member's tool_use blocks carry. Every member is an
accepted key, and a member's defaults apply wherever its key is
absent. Unknown keys are rejected: the field set is this toolset
version's complete member set.
computer_triple_click_config: object{ defer_loading, enabled }triple_click's config overrides.
triple_click's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_triple_click_input: object{ coordinate, text }Triple-click the left mouse button at the specified (x, y) pixel coordinate, or
the current cursor position if coordinate is omitted.
Triple-click the left mouse button at the specified (x, y) pixel coordinate, or
the current cursor position if coordinate is omitted.
coordinate: optional array of number(x, y): x pixels from the left edge, y pixels from the top edge.
(x, y): x pixels from the left edge, y pixels from the top edge.
Optional key combination to hold down during this action (e.g. "ctrl", "shift", "ctrl+shift").
computer_triple_click_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_type_config: object{ defer_loading, enabled }type's config overrides.
type's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_type_input: object{ text }Type a string of text on the keyboard.
Type a string of text on the keyboard.
The text to type.
computer_type_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_wait_config: object{ defer_loading, enabled }wait's config overrides.
wait's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_wait_input: object{ duration }Wait for a specified duration.
Wait for a specified duration.
duration: numberDuration to wait, in seconds.
Duration to wait, in seconds.
computer_wait_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
computer_zoom_config: object{ defer_loading, enabled }zoom's config overrides.
zoom's config overrides.
Defer loading for this member. Must resolve to the same value on every enabled member of the toolset.
Whether this member is offered to the model. Default is per member, per the toolset's documentation. A member whose enabled resolves false is withheld from the served schema.
computer_zoom_input: object{ region }Take a screenshot of a rectangular region. Region coordinates are in the
full-screenshot space (not physical display pixels). The crop is scaled up to
fill the image budget so fine details become legible.
Take a screenshot of a rectangular region. Region coordinates are in the full-screenshot space (not physical display pixels). The crop is scaled up to fill the image budget so fine details become legible.
region: array of number(x0, y0, x1, y1): The region to capture.
(x0, y0, x1, y1): The region to capture.
computer_zoom_tool_use_block: object{ type: "tool_use", id, caller, 3 more }
container: object{ id, expires_at, skills }Information about the container used in the request (for the code execution tool)
Information about the container used in the request (for the code execution tool)
Identifier for the container used in this request
expires_at: stringThe time at which the container will expire.
The time at which the container will expire.
skills: array of ContainerSkill { type, skill_id, version }Skills loaded in the container
Skills loaded in the container
type: "anthropic" or "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
skill_id: stringSkill ID
Skill ID
version: stringThe resolved version: a skill version ID for custom skills.
The resolved version: a skill version ID for custom skills.
container_params: object{ id, skills }Container parameters with skills to be loaded.
Container parameters with skills to be loaded.
Container id
skills: optional array of SkillParams { type, skill_id, version }List of skills to load in the container
List of skills to load in the container
type: "anthropic" or "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
skill_id: stringSkill ID
Skill ID
version: optional stringSkill version or 'latest' for most recent version
Skill version or 'latest' for most recent version
container_skill: object{ type, skill_id, version }A skill that was loaded in a container (response model).
A skill that was loaded in a container (response model).
type: "anthropic" or "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
skill_id: stringSkill ID
Skill ID
version: stringThe resolved version: a skill version ID for custom skills.
The resolved version: a skill version ID for custom skills.
container_upload_block: object{ type: "container_upload", file_id }Response model for a file uploaded to the container.
Response model for a file uploaded to the container.
container_upload_block_param: object{ type: "container_upload", file_id, cache_control }A content block that represents a file to be uploaded to the container
Files uploaded via this block will be available in the container's input directory.
A content block that represents a file to be uploaded to the container Files uploaded via this block will be available in the container's input directory.
cache_control: optional object{ type: "ephemeral", ttl }Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
ttl: optional "5m" or "1h"The time-to-live for the cache control breakpoint.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m. See prompt caching pricing for details.
content_block: TextBlock or ThinkingBlock or RedactedThinkingBlock or 9 more
content_block_param: TextBlockParam or ImageBlockParam or DocumentBlockParam or 13 more
content_block_source: object{ type: "content", content }
content_block_source_content: TextBlockParam or ImageBlockParam
diagnostics: object{ cache_miss_reason }Request-level diagnostics: why the prompt cache could not fully reuse
the prefix of the request named by diagnostics.previous_message_id.
Request-level diagnostics: why the prompt cache could not fully reuse
the prefix of the request named by diagnostics.previous_message_id.
diagnostics_param: object{ previous_message_id }Request-level diagnostics. Currently carries the previous response
id for prompt-cache divergence reporting.
Request-level diagnostics. Currently carries the previous response id for prompt-cache divergence reporting.
previous_message_id: optional stringThe id (msg_...) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns diagnostics.cache_miss_reason when the prompt-cache prefix could not be reused. Pass null on the first turn to opt in without a prior message to compare.
The id (msg_...) from this client's previous /v1/messages response. The server compares that request's prompt fingerprint against this one and returns diagnostics.cache_miss_reason when the prompt-cache prefix could not be reused. Pass null on the first turn to opt in without a prior message to compare.
direct_caller: object{ type: "direct" }Tool invocation directly from the model.
Tool invocation directly from the model.
document_block: object{ type: "document", citations, source, title }
document_block_param: object{ type: "document", source, cache_control, 3 more }
encrypted_code_execution_result_block: object{ type: "encrypted_code_execution_result", content, encrypted_stdout, 2 more }Code execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
content: array of CodeExecutionOutputBlock { type: "code_execution_output", file_id }
encrypted_code_execution_result_block_param: object{ type: "encrypted_code_execution_result", content, encrypted_stdout, 2 more }Code execution result with encrypted stdout for PFC + web_search results.
Code execution result with encrypted stdout for PFC + web_search results.
content: array of CodeExecutionOutputBlockParam { type: "code_execution_output", file_id }
file_document_source: object{ type: "file", file_id }
file_image_source: object{ type: "file", file_id }
image_block_param: object{ type: "image", source, cache_control, transformations }
image_transformations_param: object{ oversized_image }Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field.
Configures the transformations the server applies to this image before the model observes it. Each key names a condition the server transforms images for; its value selects the transformation applied. Omitted keys keep their default behavior, and an empty object is equivalent to omitting the field.
oversized_image: optional "downsize" or "error"What the server does when this image exceeds the model's maximum image size. "downsize" (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. "error" instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down.
What the server does when this image exceeds the model's maximum image size. "downsize" (the default) scales the image down to fit, which changes the dimensions the model observes without telling you. "error" instead rejects the request with a 400 error naming the image's dimensions and the largest dimensions that fit, so you can scale the image deliberately — your image is never silently scaled down.
input_json_delta: object{ type: "input_json_delta", partial_json }
json_output_format: object{ type: "json_schema", schema }
The JSON schema of the format
memory_tool_20250818: object{ type: "memory_20250818", name, allowed_callers, 4 more }
message: object{ type: "message", id, container, 8 more }
message_count_tokens_tool: Tool or ToolBash20250124 or CodeExecutionTool20250522 or 18 more
message_create_params_container: ContainerParams or stringContainer identifier for reuse across requests.
Container identifier for reuse across requests.
container_params: object{ id, skills }Container parameters with skills to be loaded.
Container parameters with skills to be loaded.
Container id
skills: optional array of SkillParams { type, skill_id, version }List of skills to load in the container
List of skills to load in the container
type: "anthropic" or "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
skill_id: stringSkill ID
Skill ID
version: optional stringSkill version or 'latest' for most recent version
Skill version or 'latest' for most recent version
message_delta_usage: object{ cache_creation_input_tokens, cache_read_input_tokens, input_tokens, 3 more }
message_param: object{ content, role }
message_tokens_count: object{ input_tokens }
The total number of tokens across the provided list of messages, system prompt, and tools.
metadata: object{ user_id }
user_id: optional stringAn external identifier for the user who is associated with the request.
An external identifier for the user who is associated with the request.
This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.
output_config: object{ effort, format }
effort: optional "low" or "medium" or "high" or 2 moreHow much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
How much effort the model should put into its response. Higher effort levels may result in more thorough analysis but take longer.
Valid values are low, medium, high, xhigh, or max.
format: optional object{ type: "json_schema", schema }A schema to specify Claude's output format in responses. See structured outputs
A schema to specify Claude's output format in responses. See structured outputs
The JSON schema of the format
output_tokens_details: object{ thinking_tokens }
thinking_tokens: numberNumber of output tokens the model generated as internal reasoning, including
the thinking-block delimiter tokens.
Number of output tokens the model generated as internal reasoning, including the thinking-block delimiter tokens.
Reflects the raw reasoning the model produced, not the (possibly shorter)
summarized thinking text returned in the response body. Computed by
re-tokenizing the raw reasoning text, so it may differ from the model's exact
generation count by a small number of tokens. Always ≤ output_tokens;
output_tokens - thinking_tokens approximates the non-reasoning output.
plain_text_source: object{ type: "text", data, media_type }
raw_content_block_delta: TextDelta or InputJSONDelta or CitationsDelta or 2 more
raw_content_block_delta_event: object{ type: "content_block_delta", delta, index }
raw_content_block_start_event: object{ type: "content_block_start", content_block, index }
raw_content_block_stop_event: object{ type: "content_block_stop", index }
raw_message_delta_event: object{ type: "message_delta", delta, usage }
raw_message_start_event: object{ type: "message_start", message }
raw_message_stop_event: object{ type: "message_stop" }
raw_message_stream_event: RawMessageStartEvent or RawMessageDeltaEvent or RawMessageStopEvent or 3 more
redacted_thinking_block: object{ type: "redacted_thinking", data }
data: stringThe contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content.
The contents of this redacted thinking block, returned when portions of the model's thinking were safety-redacted. This field is opaque and encrypted, with no readable content.
Pass redacted_thinking blocks back to the API unchanged when continuing a multi-turn conversation.
See extended thinking for details.
redacted_thinking_block_param: object{ type: "redacted_thinking", data }
The data value of this redacted thinking block, exactly as returned by the API in a previous response. Opaque and encrypted; pass it back unchanged.
refusal_stop_details: object{ type: "refusal", category, explanation }Structured information about a refusal.
Structured information about a refusal.
category: "cyber" or "bio" or "frontier_llm" or 2 moreThe policy category that triggered the refusal.
The policy category that triggered the refusal.
null when the refusal doesn't map to a named category.
The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.
The request could assist the development of competing AI models, which is restricted under Anthropic's commercial terms. Benign machine learning work can also trigger this category.
The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use adaptive thinking.
The request could be related to an area that was determined as harmful. Benign work might sometimes trigger this category.
explanation: stringHuman-readable explanation of the refusal.
Human-readable explanation of the refusal.
This text is not guaranteed to be stable. null when no explanation is available for the category.
search_result_block_param: object{ type: "search_result", content, source, 3 more }
server_tool_caller: object{ type: "code_execution_20250825", tool_id }Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
tool_id: string
server_tool_caller_20260120: object{ type: "code_execution_20260120", tool_id }
tool_id: string
server_tool_usage: object{ web_fetch_requests, web_search_requests }
web_fetch_requests: numberThe number of web fetch tool requests.
The number of web fetch tool requests.
web_search_requests: numberThe number of web search tool requests.
The number of web search tool requests.
server_tool_use_block: object{ type: "server_tool_use", id, caller, 2 more }
server_tool_use_block_param: object{ type: "server_tool_use", id, input, 3 more }
signature_delta: object{ type: "signature_delta", signature }
The signature for this thinking block: an opaque value used to verify that the block was generated by Claude when it is passed back to the API. Delivered in a signature_delta event just before the block's content_block_stop event.
skill_params: object{ type, skill_id, version }Specification for a skill to be loaded in a container (request model).
Specification for a skill to be loaded in a container (request model).
type: "anthropic" or "custom"Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
Type of skill - either 'anthropic' (built-in) or 'custom' (user-defined)
skill_id: stringSkill ID
Skill ID
version: optional stringSkill version or 'latest' for most recent version
Skill version or 'latest' for most recent version
stop_reason: "end_turn" or "max_tokens" or "stop_sequence" or 4 more
text_block: object{ type: "text", citations, text }
text_block_param: object{ type: "text", text, cache_control, citations }
text_citation: CitationCharLocation or CitationPageLocation or CitationContentBlockLocation or 2 more
text_citation_param: CitationCharLocationParam or CitationPageLocationParam or CitationContentBlockLocationParam or 2 more
text_delta: object{ type: "text_delta", text }
text_editor_code_execution_create_result_block: object{ type: "text_editor_code_execution_create_result", is_file_update }
text_editor_code_execution_create_result_block_param: object{ type: "text_editor_code_execution_create_result", is_file_update }
text_editor_code_execution_str_replace_result_block: object{ type: "text_editor_code_execution_str_replace_result", lines, new_lines, 3 more }
text_editor_code_execution_str_replace_result_block_param: object{ type: "text_editor_code_execution_str_replace_result", lines, new_lines, 3 more }
text_editor_code_execution_tool_result_block: object{ type: "text_editor_code_execution_tool_result", content, tool_use_id }
text_editor_code_execution_tool_result_block_param: object{ type: "text_editor_code_execution_tool_result", content, tool_use_id, cache_control }
text_editor_code_execution_tool_result_error: object{ type: "text_editor_code_execution_tool_result_error", error_code, error_message }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
text_editor_code_execution_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
text_editor_code_execution_tool_result_error_param: object{ type: "text_editor_code_execution_tool_result_error", error_code, error_message }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or 2 more
text_editor_code_execution_view_result_block: object{ type: "text_editor_code_execution_view_result", content, file_type, 3 more }
file_type: "text" or "image" or "pdf"
text_editor_code_execution_view_result_block_param: object{ type: "text_editor_code_execution_view_result", content, file_type, 3 more }
file_type: "text" or "image" or "pdf"
thinking_block: object{ type: "thinking", signature, thinking }
signature: stringA value used to verify that this thinking block was generated by Claude when it is passed back to the API.
A value used to verify that this thinking block was generated by Claude when it is passed back to the API.
This is an opaque field and should not be interpreted or parsed. When passing thinking blocks back to the API (required when using tools with extended thinking), pass them back exactly as received, with this field intact.
See extended thinking for details.
The text of Claude's thinking process for this block.
thinking_block_param: object{ type: "thinking", signature, thinking }
signature: stringThe signature value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude.
The signature value of this thinking block, exactly as returned by the API in a previous response. Used to verify that the block was generated by Claude.
Thinking blocks must be passed back unmodified and in their original order; a modified block results in a 400 invalid_request_error.
The thinking text of this block as returned by the API.
thinking_config_adaptive: object{ type: "adaptive", display }
display: optional "summarized" or "omitted"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. The default depends on the model; see Controlling thinking display.
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. The default depends on the model; see Controlling thinking display.
thinking_config_between_tools: object{ type: "between_tools" }
thinking_config_disabled: object{ type: "disabled" }
thinking_config_enabled: object{ type: "enabled", budget_tokens, display }
budget_tokens: numberDetermines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.
Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality.
Must be ≥1024 and less than max_tokens.
See extended thinking for details.
display: optional "summarized" or "omitted"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. The default depends on the model; see Controlling thinking display.
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. The default depends on the model; see Controlling thinking display.
thinking_config_param: ThinkingConfigEnabled or ThinkingConfigDisabled or ThinkingConfigBetweenTools or ThinkingConfigAdaptiveConfiguration for Claude's thinking.
Configuration for Claude's thinking.
With {"type": "adaptive"}, Claude decides when and how much to think. With {"type": "enabled"} (manual extended thinking), you set a budget_tokens of at least 1,024. Thinking tokens count toward your max_tokens limit.
Which type values are accepted, and what happens when you omit thinking, depend on the model. See thinking for each model's behavior.
thinking_delta: object{ type: "thinking_delta", thinking }
The incremental thinking text for this content block. Concatenate the thinking values of successive thinking_delta events to assemble the block's full thinking value.
tool: object{ type: "custom", input_schema, name, 7 more }
tool_bash_20250124: object{ type: "bash_20250124", name, allowed_callers, 4 more }
tool_choice: ToolChoiceAuto or ToolChoiceAny or ToolChoiceTool or ToolChoiceNoneHow 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.
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.
tool_choice_any: object{ type: "any", disable_parallel_tool_use }The model will use any available tools.
The model will use any available tools.
disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
tool_choice_auto: object{ type: "auto", disable_parallel_tool_use }The model will automatically decide whether to use tools.
The model will automatically decide whether to use tools.
disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output at most one tool use.
tool_choice_none: object{ type: "none" }The model will not be allowed to use tools.
The model will not be allowed to use tools.
tool_choice_tool: object{ type: "tool", name, disable_parallel_tool_use }The model will use the specified tool with tool_choice.name.
The model will use the specified tool with tool_choice.name.
The name of the tool to use.
disable_parallel_tool_use: optional booleanWhether to disable parallel tool use.
Whether to disable parallel tool use.
Defaults to false. If set to true, the model will output exactly one tool use.
tool_reference_block: object{ type: "tool_reference", tool_name }
tool_name: string
tool_reference_block_param: object{ type: "tool_reference", tool_name, cache_control }Tool reference block that can be included in tool_result content.
Tool reference block that can be included in tool_result content.
tool_name: string
cache_control: optional object{ type: "ephemeral", ttl }Create a cache control breakpoint at this content block.
Create a cache control breakpoint at this content block.
ttl: optional "5m" or "1h"The time-to-live for the cache control breakpoint.
The time-to-live for the cache control breakpoint.
This may be one the following values:
5m: 5 minutes1h: 1 hour
Defaults to 5m. See prompt caching pricing for details.
tool_result_block_param: object{ type: "tool_result", tool_use_id, cache_control, 3 more }
tool_search_tool_bm25_20251119: object{ type, name, allowed_callers, 3 more }
tool_search_tool_regex_20251119: object{ type, name, allowed_callers, 3 more }
tool_search_tool_result_block: object{ type: "tool_search_tool_result", content, tool_use_id }
tool_search_tool_result_block_param: object{ type: "tool_search_tool_result", content, tool_use_id, cache_control }
tool_search_tool_result_error: object{ type: "tool_search_tool_result_error", error_code, error_message }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
tool_search_tool_result_error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
tool_search_tool_result_error_param: object{ type: "tool_search_tool_result_error", error_code, error_message }
error_code: "invalid_tool_input" or "unavailable" or "too_many_requests" or "execution_time_exceeded"
tool_search_tool_search_result_block: object{ type: "tool_search_tool_search_result", tool_references }
tool_references: array of ToolReferenceBlock { type: "tool_reference", tool_name }
tool_name: string
tool_search_tool_search_result_block_param: object{ type: "tool_search_tool_search_result", tool_references }
tool_text_editor_20250124: object{ type: "text_editor_20250124", name, allowed_callers, 4 more }
tool_text_editor_20250429: object{ type: "text_editor_20250429", name, allowed_callers, 4 more }
tool_text_editor_20250728: object{ type: "text_editor_20250728", name, allowed_callers, 5 more }
tool_union: Tool or ToolBash20250124 or CodeExecutionTool20250522 or 18 more
tool_use_block: object{ type: "tool_use", id, caller, 3 more }
tool_use_block_param: object{ type: "tool_use", id, input, 4 more }
tool_use_caller: DirectCaller or ServerToolCaller or ServerToolCaller20260120Which party invoked the tool call: the model directly, or a server tool on its behalf.
Which party invoked the tool call: the model directly, or a server tool on its behalf.
direct_caller: object{ type: "direct" }Tool invocation directly from the model.
Tool invocation directly from the model.
server_tool_caller: object{ type: "code_execution_20250825", tool_id }Tool invocation generated by a server-side tool.
Tool invocation generated by a server-side tool.
tool_id: string
server_tool_caller_20260120: object{ type: "code_execution_20260120", tool_id }
tool_id: string
toolset_tool_use_block: BrowserToolUseBlock or ComputerToolUseBlock or ToolUseBlock
url_image_source: object{ type: "url", url }
url_pdf_source: object{ type: "url", url }
usage: object{ cache_creation, cache_creation_input_tokens, cache_read_input_tokens, 6 more }
user_location: object{ type: "approximate", city, country, 2 more }
city: optional stringThe city of the user.
The city of the user.
country: optional stringThe two letter ISO country code of the user.
The two letter ISO country code of the user.
region: optional stringThe region of the user.
The region of the user.
timezone: optional stringThe IANA timezone of the user.
The IANA timezone of the user.
web_fetch_block: object{ type: "web_fetch_result", content, retrieved_at, url }
web_fetch_block_param: object{ type: "web_fetch_result", content, url, retrieved_at }
web_fetch_tool_20250910: object{ type: "web_fetch_20250910", name, allowed_callers, 9 more }
web_fetch_tool_20260209: object{ type: "web_fetch_20260209", name, allowed_callers, 9 more }
web_fetch_tool_20260309: object{ type: "web_fetch_20260309", name, allowed_callers, 10 more }Web fetch tool with use_cache parameter for bypassing cached content.
Web fetch tool with use_cache parameter for bypassing cached content.
web_fetch_tool_20260318: object{ type: "web_fetch_20260318", name, allowed_callers, 11 more }
web_fetch_tool_result_block: object{ type: "web_fetch_tool_result", caller, content, tool_use_id }
web_fetch_tool_result_block_param: object{ type: "web_fetch_tool_result", content, tool_use_id, 2 more }
web_fetch_tool_result_error_block: object{ type: "web_fetch_tool_result_error", error_code }
error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more
web_fetch_tool_result_error_block_param: object{ type: "web_fetch_tool_result_error", error_code }
error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more
web_fetch_tool_result_error_code: "invalid_tool_input" or "url_too_long" or "url_not_allowed" or 7 more
web_fetch_url_source_all: object{ type: "all" }The url_sources variant under which a source contributes in
full: every result of the tool filter's source, or all user input.
The url_sources variant under which a source contributes in
full: every result of the tool filter's source, or all user input.
web_fetch_url_source_except: object{ type: "except", tools }The tool filter variant under which every result but the named
tools' contributes.
The tool filter variant under which every result but the named tools' contributes.
tools: array of WebFetchURLSourceToolReference { type: "tool_reference", name }
web_fetch_url_source_none: object{ type: "none" }The url_sources variant under which a source contributes nothing:
no result of the tool filter's source, or no user input.
The url_sources variant under which a source contributes nothing:
no result of the tool filter's source, or no user input.
web_fetch_url_source_only: object{ type: "only", tools }The tool filter variant under which only the named tools' results
contribute.
The tool filter variant under which only the named tools' results contribute.
tools: array of WebFetchURLSourceToolReference { type: "tool_reference", name }
web_fetch_url_source_tool_reference: object{ type: "tool_reference", name }One entry of a tool filter's tools: it must name a tool declared
in this request's tools[].
One entry of a tool filter's tools: it must name a tool declared
in this request's tools[].
web_fetch_url_sources: object{ client_tool_results, server_tool_results, user_input }Which sources contribute to the set of URLs web fetch may fetch.
Which sources contribute to the set of URLs web fetch may fetch.
Each key is a tagged variant: user_input is all or none; the
two tool filters are all, none, only (only the named tools'
results) or except (every result but the named tools'). A named tool
must be declared in this request's tools[].
web_search_result_block: object{ type: "web_search_result", encrypted_content, page_age, 2 more }
web_search_result_block_param: object{ type: "web_search_result", encrypted_content, title, 2 more }
web_search_tool_20250305: object{ type: "web_search_20250305", name, allowed_callers, 7 more }
web_search_tool_20260209: object{ type: "web_search_20260209", name, allowed_callers, 7 more }
web_search_tool_20260318: object{ type: "web_search_20260318", name, allowed_callers, 8 more }
web_search_tool_request_error: object{ type: "web_search_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more
web_search_tool_result_block: object{ type: "web_search_tool_result", caller, content, tool_use_id }
web_search_tool_result_block_content: WebSearchToolResultError or array of WebSearchResultBlock
web_search_tool_result_block_param: object{ type: "web_search_tool_result", content, tool_use_id, 2 more }
web_search_tool_result_block_param_content: array of WebSearchResultBlockParam or WebSearchToolRequestError
web_search_tool_result_error: object{ type: "web_search_tool_result_error", error_code }
error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more
web_search_tool_result_error_code: "invalid_tool_input" or "unavailable" or "max_uses_exceeded" or 3 more
MessagesBatches
Create a Message Batch
$ ant messages:batches createSend a batch of Message creation requests.
Retrieve a Message Batch
$ ant messages:batches retrieveThis endpoint is idempotent and can be used to poll for Message Batch completion. To access the results of a Message Batch, make a request to the results_url field in the response.
List Message Batches
$ ant messages:batches listList all Message Batches within a Workspace. Most recently created batches are returned first.
Cancel a Message Batch
$ ant messages:batches cancelBatches may be canceled any time before processing ends. Once cancellation is initiated, the batch enters a canceling state, at which time the system may complete any in-progress, non-interruptible requests before finalizing cancellation.
Retrieve Message Batch results
$ ant messages:batches resultsStreams the results of a Message Batch as a .jsonl file.