GET

/v1/schemas/moonshot/chat/v1/responses?kind=output

Accept:

kind outputactivity chathash e41fa071…extracted Sep 19, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `3ae22621b735ced993ea3f670c119ae4b4c090dece83779ee3954414be11f6da` { "fetchedAt": 1789794729, "extractorVersion": "1", "verifiedAt": null }

Response body

26 properties · 0 required · 13 $defs

property	type	description	constraints
id	string	Unique identifier of the response.
object	enum		response
created_at	integer	Unix timestamp of when the response was created.
completed_at	any	Unix timestamp of when the response finished. Present when `status` is `completed` or `incomplete`; `null` when `status` is `in_progress` or `failed`.
status	enum	Response status. The opening snapshot of a stream is `in_progress`.	in_progress \| completed \| incomplete \| failed
model	string	Model that produced the response.
output	ResponsesOutputItem[]	The output item array, ordered as web_search_call (if any), reasoning, message, tool calls.
usage	ResponsesUsage	Token usage for this response.	nullable
incomplete_details	object	Reason the response is `incomplete`.
error	object	Error information when `status` is `failed`.
instructions	any
reasoning	any
text	any
tools	any
tool_choice	enum	Controls tool-calling behavior. With `auto`, the model decides whether to call a tool.	auto · nullable
max_output_tokens	any
temperature	any
top_p	any
metadata	any
parallel_tool_calls	boolean
service_tier	any
store	boolean	Always `false`.
background	any	Always `false`.
previous_response_id	any	Always `null`.
conversation	any	Always `null`.
prompt_cache_options	object	The context cache write options actually applied by the server. When the request omits prompt_cache_options, refer to the mode and ttl returned here

Types

13 $defs

ResponsesCustomToolobject

A custom tool that takes free-form text input. Only the custom tool named `apply_patch` is supported, and it must define a `grammar` + `lark` format; when the model calls it, a `custom_tool_call` item is returned in the output.

type*	enum		custom
name*	enum	Tool name. Only `apply_patch` is supported.	apply_patch
description	string
format*	object	Input format constraint. Only the `grammar` type with `lark` syntax is supported.

ResponsesFunctionToolobject

A function tool whose arguments are described by a JSON Schema.

type*	enum		function
name*	string	Function name. Must follow the regex: ^[a-zA-Z_][a-zA-Z0-9-_]{0,127}$
description	string
parameters	object	JSON Schema describing the function arguments.
strict	boolean

ResponsesNamespaceToolobject

Groups a set of function or custom tools under one namespace.

type*	enum	namespace
name*	string
description*	string
tools*	ResponsesFunctionTool \| ResponsesCustomTool[]

ResponsesOutputCustomToolCallItemobject

A custom tool call initiated by the model.

type	enum		custom_tool_call
id	string
call_id	string	Use this value in `custom_tool_call_output` when returning the result.
name	string
namespace	string	Returned for namespace tool calls.
input	string	Free-form text input generated by the model.
status	enum		in_progress \| completed

ResponsesOutputFunctionCallItemobject

A function call initiated by the model.

type	enum		function_call
id	string
call_id	string	Use this value in `function_call_output` when returning the result.
name	string
namespace	string	Returned for namespace tool calls.
arguments	string	JSON string of the function arguments.
status	enum		in_progress \| completed

ResponsesOutputItemReasoning | Message | Function call | …

An element of the output array, discriminated by `type`.

ResponsesOutputMessageItemobject

Text reply produced by the model.

type	enum	message
id	string
role	enum	assistant
content	object[]
status	enum	in_progress \| completed

ResponsesOutputReasoningItemobject

Reasoning content produced by the model.

type	enum		reasoning
id	string
summary	object[]	The reasoning content.
encrypted_content	any	Always `null`.
status	enum		in_progress \| completed

ResponsesOutputWebSearchCallItemobject

A web search call executed on the server side. Returned only when the request includes the `web_search` tool and the server decides a search is needed. It appears first in the output array.

type	enum		web_search_call
id	string
status	enum		in_progress \| completed
action	object	The action performed by this search.
results	object[]	Image search results. Returned only when `include` contains `web_search_call.results` and `search_content_types` includes `image`.

ResponsesToolFunction tool | Custom tool | Namespace tool | …

A tool definition, discriminated by `type`. Supported types are `function`, `custom` (only `apply_patch`), `namespace`, and `web_search`; other tool types are not supported.

ResponsesToolChoiceenum

Controls tool-calling behavior. With `auto`, the model decides whether to call a tool.

auto

ResponsesUsageobject

Token usage for this response.

input_tokens	integer	Number of input tokens, including cached tokens.
input_tokens_details	object
output_tokens	integer	Number of output tokens, including reasoning tokens.
output_tokens_details	object
total_tokens	integer	Total number of tokens.

ResponsesWebSearchToolobject

A web search tool executed on the server side. When present, the server first decides from the input whether a search is needed; if so, it runs the search, injects the results into the model context, and returns a `web_search_call` item in the output. At most …

type*	enum		web_search
filters	object	Search scope filters.
search_content_types	enum[]	Result types to search for. Defaults to `text` only. Including `image` additionally runs an image search.	default: ["text"]
image_settings	object	Image search settings. Only effective when `search_content_types` includes `image`.

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"moonshot","endpointId":"v1/responses","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}