GET

/v1/schemas/nvidia/chat/mistralai/mistral-large-4-1t-a52b

Accept:

kind inputactivity chathash 9e2d58ec…extracted Nov 4, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `ebfe25f4ddecce0ee1795328b0754c7d952d177172c5f58e0b80cce2d0e81024` { "fetchedAt": 1793769657, "extractorVersion": "1", "verifiedAt": null }

Request body

13 properties · 2 required · 4 $defs

property	type	description	constraints
model*	enum		mistralai/mistral-large-4-1t-a5… · default: "mistralai/mistral-large-4-1t-a5…
messages*	ChatMessage[]	Conversation history. Use content-part arrays for images. After an assistant tool call, include a tool message with its tool_call_id. Preserve assistant reasoning_content when continuing a conversation.	items ≥ 1 · default: [{"role":"user","content":"What …
max_tokens	integer	Maximum generated tokens, including reasoning and the final answer. Small budgets may end during reasoning with null content and finish_reason=length. Prompt plus output must fit the context window.	1 ≤ n ≤ 262144 · default: 4096
stream	boolean		default: false
temperature	number	The sampling temperature to use for text generation. The higher the temperature value is, the less deterministic the output text will be. It is not recommended to modify both temperature and top_p in the same call.	0 ≤ n ≤ 2 · default: 0.5
top_p	number	The top-p sampling mass used for text generation. The top-p value determines the probability mass that is sampled at sampling time. For example, if top_p = 0.2, only the most likely tokens (summing to 0.2 cumulative probability) will be sampled. It is not reco…	0 < n ≤ 1 · default: 1
frequency_penalty	number	Indicates how much to penalize new tokens based on their existing frequency in the text so far, decreasing model likelihood to repeat the same line verbatim.	-2 ≤ n ≤ 2 · default: 0
presence_penalty	number	Positive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics.	-2 ≤ n ≤ 2 · default: 0
seed	integer	Optional sampling seed, limited to JavaScript-safe integers for the interactive examples. Deterministic output is not guaranteed.	0 ≤ n ≤ 9007199254740991
stop	string \| string[]	Stop string or list of stop strings; omitted from the output.	nullable
tools	FunctionTool[]	Functions the model may request; the caller executes them.
tool_choice	enum \| object	Choose auto, none, required, or force a named function.
reasoning_effort	enum	Controls reasoning for this request. Set to high, the model reasons first and the response carries reasoning_content separately from the final content; set to none, it answers directly. The playground sends high by default; a request that omits this field is s…	none \| high · default: "high"

Types

4 $defs

ChatMessageobject

role*	enum		system \| user \| assistant \| tool
content	string \| ContentPart[]	Message text or content parts. Required except on an assistant message that carries tool_calls, where it may be null.	nullable
reasoning_content	any	Assistant reasoning, separate from the final answer.
tool_calls	ToolCall[]
tool_call_id	string	Required on tool-result messages; matches an assistant tool call ID.
name	string

ContentPartobject | object

FunctionToolobject

type*	enum		function · default: "function"
function*	object

ToolCallobject

id*	string
type*	enum	function · default: "function"
function*	object

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"nvidia","endpointId":"mistralai/mistral-large-4-1t-a52b","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}