Endpoint Details
Review how to make this request and handle its possible responses.
https://integrate.api.nvidia.com/v1/chat/completionsSupports text, up to eight images, function tools, and streaming. Video and audio inputs are unsupported. With stream=true, consume data-only SSE events until data: [DONE]; reasoning, content, and tool calls arrive as deltas.
Request Body
Edit the request fields below.
Request details
Parameters13 Parameters
modelrequiredmistralai/mistral-large-4-1t-a52bValid values: mistralai/mistral-large-4-1t-a52bmessagesrequiredConversation 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.
[{"role":"user","content":"What is 37 + 58? Reply with only the number."}]Example: [{"role":"user","content":"What is 37 + 58? Reply with only the number."}]Minimum items: 1messages[].rolerequiredsystem · user · assistant · toolmessages[].contentoptionalMessage text or content parts. Required except on an assistant message that carries tool_calls, where it may be null.
messages[].reasoning_contentoptionalAssistant reasoning, separate from the final answer.
messages[].tool_callsoptionalmessages[].tool_call_idoptionalRequired on tool-result messages; matches an assistant tool call ID.
messages[].nameoptionalmax_tokensoptionalMaximum 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.
4096Minimum: 1Maximum: 262144streamoptionalfalsetemperatureoptionalThe 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.
0.5Minimum: 0Maximum: 2top_poptionalThe 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 recommended to modify both temperature and top_p in the same call.
1Maximum: 1Exclusive minimum: 0frequency_penaltyoptionalIndicates 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.
0Minimum: -2Maximum: 2presence_penaltyoptionalPositive values penalize new tokens based on whether they appear in the text so far, increasing model likelihood to talk about new topics.
0Minimum: -2Maximum: 2seedoptionalOptional sampling seed, limited to JavaScript-safe integers for the interactive examples. Deterministic output is not guaranteed.
0Maximum: 9007199254740991stopoptionalStop string or list of stop strings; omitted from the output.
toolsoptionalFunctions the model may request; the caller executes them.
tool_choiceoptionalChoose auto, none, required, or force a named function.
reasoning_effortoptionalControls 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 served as none. chat_template_kwargs.enable_thinking is not honored by this recipe.
highValid values: none · highHeaders3 Headers
AuthorizationrequiredFormat: Bearer $NVIDIA_API_KEY
Content-TyperequiredAcceptoptional