GET

/v1/schemas/grok/chat/v1/chat/completions?kind=output

Accept:

kind outputactivity chathash 00ee0577…extracted Sep 24, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `9d3bba5a4bc352e14d619266f397ca689140f67989db997818ba2747dfb0765b` { "fetchedAt": 1790226635, "extractorVersion": "1", "verifiedAt": null }

Response body

10 properties · 6 required · 13 $defs

property	type	description	constraints
choices*	Choice[]	A list of response choices from the model. The length corresponds to the `n` in request body (default to 1).
created*	integer	The chat completion creation time in Unix timestamp.	format: int64
id*	string	A unique ID for the chat response.
model*	string	Model ID used to create chat completion.
object*	string	The object type, which is always `"chat.completion"`.
service_tier*	enum	The processing tier used for this request.	default \| priority \| fast
citations	any	List of all the external pages used by the model to answer.
output_files	any	Files generated during the response (e.g., by the code execution tool). Only populated when `code_execution_files_output` is included.
system_fingerprint	any	System fingerprint, used to indicate xAI system configuration changes.
usage	Usage	Token usage information.	nullable

Types

13 $defs

Choiceobject

finish_reason	any	Finish reason. `"stop"` means the inference has reached a model-defined or user-supplied stop sequence in `stop`. `"length"` means the inference result has reached models' maximum allowed token length or user defined value in `max_tokens`. `"end_turn"` or `nul…
index*	integer	Index of the choice within the response choices, starting from 0.	format: int32
logprobs	LogProbs	The log probabilities of each output token returned in the content of message.	nullable
message*	ChoiceMessage	The generated chat completion message.

ChoiceMessageobject

content	any	The content of the message.
reasoning_content	any	The reasoning trace generated by the model.
refusal	any	The reason given by model if the model is unable to generate a response. null if model is able to generate.
role*	string	The role that the message belongs to, the response from model is always `"assistant"`.
tool_calls	any	A list of tool calls asked by model for user to perform.

CompletionUsageDetailobject

Details of completion usage.

accepted_prediction_tokens*	integer	The number of tokens in the prediction that appeared in the completion.	format: int32
audio_tokens*	integer	Audio input tokens generated by the model.	format: int32
reasoning_tokens*	integer	Tokens generated by the model for reasoning.	format: int32
rejected_prediction_tokens*	integer	The number of tokens in the prediction that did not appear in the completion.	format: int32

Functionobject

arguments*	string
name*	string

LogProbsobject

content

any

An array the log probabilities of each output token returned.

OutputFileobject

A file generated during the model's response (e.g., by the code execution tool).

file_id*	string	The file ID from the Files API. Use this to download the file.
name*	string	The display name of the file.

PromptUsageDetailobject

Details of prompt usage.

audio_tokens*	integer	Audio prompt token used.	format: int32
cached_tokens*	integer	Token cached by xAI from previous requests and reused for this request.	format: int32
image_tokens*	integer	Image prompt token used.	format: int32
text_tokens*	integer	Total text prompt token used (cached + non-cached text tokens).	format: int32

ServerSideToolUsageDetailsobject

code_interpreter_calls*	integer	Number of code interpreter calls.	format: int32
document_search_calls*	integer	Number of document search calls.	format: int32
file_search_calls*	integer	Number of file search calls.	format: int32
image_generation_calls*	integer	Number of image generation calls.	format: int32
mcp_calls*	integer	Number of MCP calls.	format: int32
web_search_calls*	integer	Number of web search calls.	format: int32
x_posts_fetched*	integer	Number of X posts fetched across all X search calls, including nested parent/quote posts and every post of a fetched thread, without de-duplication. X search is billed per fetched item.	format: int32
x_search_calls*	integer	Number of X search calls.	format: int32
x_users_fetched*	integer	Number of X user profiles fetched across all X search calls, without de-duplication. X search is billed per fetched item.	format: int32

ServiceTierenum

Processing tier for a request. `Fast` and `Priority` are interchangeable: the model's fast deployment and its rates where configured, else higher scheduling priority at a higher price.

default | priority | fast

TokenLogProbobject

bytes	any	The ASCII encoding of the output character.
logprob*	number	The log probability of returning this token.	format: float
token*	string	The token.
top_logprobs*	TopLogProb[]	An array of the most likely tokens to return at this token position.

ToolCallobject

function*	Function	Function to call for the tool call.
id*	string	A unique ID of the tool call generated by xAI. After performing tool call's function, user provides this ID with tool call's result in the subsequent request to xAI. xAI can then match the tool call result sent with tool call request.
index	any	Index of the tool call.	format: int32
type	any	Type of tool call, should be `"function"` or `"web_search_call"` or `"x_search_call"` or `"code_interpreter_call"` or `"mcp_call"`

TopLogProbobject

bytes	any	The ASCII encoding of the output character.
logprob*	number	The log probability of returning this token.	format: float
token*	string	The token.

Usageobject

completion_tokens*	integer	Total completion token used.	format: int32
completion_tokens_details*	CompletionUsageDetail	Breakdown of completion token usage of different types.
cost_in_usd_ticks*	integer	Accurate cost of this request in USD ticks, where "tick" is defined as follows: TICKS_IN_USD_CENT: i64 = 100_000_000 which means there is 10'000'000'000 ticks in one dollar.	format: int64
num_sources_used*	integer	Number of individual live search source used.	format: int32
prompt_tokens*	integer	Total prompt token used.	format: int32
prompt_tokens_details*	PromptUsageDetail	Breakdown of prompt token usage of different types.
server_side_tool_usage_details	ServerSideToolUsageDetails	Details about the server side tool usage.	nullable
total_tokens*	integer	Total token used, the sum of prompt token and completion token amount.	format: int32

Validate a payload

before you spend tokens

shell

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