GET

/v1/schemas/groq/chat/openai/v1/responses?kind=output

Accept:

kind outputactivity chathash 7d20a33a…extracted Sep 20, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `372870924527dbca12a2921eec01c3d9c8a5d7023e53f7249c8508c7601a0606` { "fetchedAt": 1789881684, "extractorVersion": "1", "verifiedAt": null }

Response body

27 properties · 17 required · 18 $defs

property	type	description	constraints
id*	string	A unique identifier for the response.
object*	enum	The object type, which is always `response`.	response
status*	enum	The status of the response generation. One of `completed`, `failed`, `in_progress`, or `incomplete`.	completed \| failed \| in_progress \| incomplete
created_at*	integer	The Unix timestamp (in seconds) of when the response was created.
output*	ResponseOutputItem[]	An array of content items generated by the model.
model*	string	The model used for the response.
tools*	ResponseTool[]	The tools that were available to the model.
tool_choice*	enum \| object	Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call …
truncation*	enum	The truncation strategy used.	auto \| disabled
metadata*	object	Metadata attached to the response.
temperature*	number	The sampling temperature used.
top_p*	number	The nucleus sampling parameter used.
service_tier*	enum	The service tier used for processing.	auto \| default \| flex
error*	object	An error object if the response failed.
incomplete_details*	object	Details about why the response is incomplete.
parallel_tool_calls*	boolean	Whether the model can run tool calls in parallel.
store*	boolean	Whether the response was stored.
previous_response_id	string	Not supported. Always null.
reasoning	object	Configuration options for [models that support reasoning](https://console.groq.com/docs/reasoning).
max_output_tokens	integer	The maximum number of tokens configured for the response.
instructions	string	The system instructions used for the response.
text	object	Text format configuration used for the response.
user	string	The user identifier.
usage	ResponseUsage	Usage statistics for the response request.
background	boolean	Whether the response was generated in the background.	default: false
top_logprobs	integer	The number of top log probabilities returned.	default: 0
max_tool_calls	integer	The maximum number of tool calls allowed.

Types

18 $defs

FunctionParametersobject

Function parameters defined as a JSON Schema object. Refer to https://json-schema.org/understanding-json-schema/ for schema documentation.

ResponseAnnotationFile citation | URL citation

ResponseFileCitationobject

A citation to a file.

type*	enum	The type of the annotation. Always `file_citation`.	file_citation
file_id*	string	The ID of the file.
index	integer	The index of the citation in the text.

ResponseFormatConfigurationText | JSON object | JSON schema

An object specifying the format that the model must output.

ResponseFormatJsonObjectobject

JSON object response format. An older method of generating JSON responses. Using `json_schema` is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.

type*

enum

The type of response format being defined. Always `json_object`.

json_object

ResponseFormatTextobject

Default response format. Used to generate text responses.

type*

enum

The type of response format being defined. Always `text`.

text

ResponseNamedToolChoiceobject

Specifies a tool the model should use. Use to force the model to call a specific function.

type*	enum	The type of the tool. Currently, only `function` is supported.	function
function*	object

ResponseOutputContentResponseOutputTextContent

A text output from the model.

type*	enum	The type of the output text. Always `output_text`.	output_text
text*	string	The text output from the model.
annotations*	ResponseAnnotation[]	The annotations of the text output.
logprobs	string[]	Log probability information for the output.

ResponseOutputFunctionCallobject

A function call generated by the model.

type*	enum	The type of the function call. Always `function_call`.	function_call
id*	string	The unique ID of the function tool call.
status	enum	The status of the function call.	in_progress \| completed \| incomplete
call_id*	string	The unique ID of the function tool call generated by the model.
name*	string	The name of the function to call.
arguments*	string	A JSON string of the arguments to pass to the function.

ResponseOutputItemOutput message | Function call | Reasoning

ResponseOutputMessageobject

An output message from the model.

type*	enum	The type of the output message. Always `message`.	message
id*	string	The unique ID of the output message.
status	enum	The status of the message.	in_progress \| completed \| incomplete
role*	enum	The role of the output message. Always `assistant`.	assistant
content*	ResponseOutputContent[]	The content of the output message.

ResponseOutputReasoningobject

A reasoning output from the model. Available for [models that support reasoning](https://console.groq.com/docs/reasoning).

type*	enum	The type of the reasoning output. Always `reasoning`.	reasoning
id*	string	The unique ID of the reasoning output.
summary*	object[]	Summary items (currently empty).

ResponseOutputTextContentobject

A text output from the model.

type*	enum	The type of the output text. Always `output_text`.	output_text
text*	string	The text output from the model.
annotations*	ResponseAnnotation[]	The annotations of the text output.
logprobs	string[]	Log probability information for the output.

ResponseToolobject

type*	enum	The type of the tool. Currently, only `function` is supported.	function
name*	string	The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
description	string	Describes the function's purpose. The model uses this to determine when to invoke the function.
parameters	FunctionParameters	Function parameters defined as a JSON Schema object. Refer to https://json-schema.org/understanding-json-schema/ for schema documentation.
strict	boolean	Whether to enable strict schema adherence when generating the function call.

ResponseToolChoiceOptionenum | object

Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call …

ResponseUrlCitationobject

A citation for a web resource.

type*	enum	The type of the annotation. Always `url_citation`.	url_citation
url*	string	The URL of the web resource.
start_index	integer	The index of the first character of the URL citation in the message.
end_index	integer	The index of the last character of the URL citation in the message.
title	string	The title of the web resource.

ResponseUsageobject

Usage statistics for the response request.

input_tokens*	integer	Number of tokens in the input.
input_tokens_details*	object	Breakdown of input tokens.
output_tokens*	integer	Number of tokens in the generated output.
output_tokens_details*	object	Breakdown of output tokens.
total_tokens*	integer	Total number of tokens used in the request (input + output).

TextResponseFormatJsonSchemaobject

JSON Schema response format. Used to generate structured JSON responses.

type*	enum	The type of response format being defined. Always `json_schema`.	json_schema
name*	string	The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
description	string	A description of what the response format is for, used by the model to determine how to respond in the format.
schema*	object	The schema for the response format, described as a JSON Schema object.
strict	boolean	Whether to enable strict schema adherence when generating the output.	default: false

Validate a payload

before you spend tokens

shell

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