Endpoint Details
Review how to make this request and handle its possible responses.
https://integrate.api.nvidia.com/v1/chat/completionsInvokes inference using the model chat parameters.
Request Body
Edit the request fields below.
Request details
Parameters9 Parameters
messagesrequiredA list of messages comprising the conversation so far.
1messages[].rolerequiredThe role of the message's author.
messages[].contentrequiredThe contents of the message. <br>To pass media (only with role=`user`): <br> - Use content parts. Text is passed with `type`=`text`. <br> - Images are passed with `type`=`image_url`; set `image_url.url` to an image URL or a base64 data URI like `data:image/{format};base64,{base64encodedimage}`. <br> - Videos are passed with `type`=`video_url`; set `video_url.url` to a video URL or a base64 data URI like `data:video/mp4;base64,{base64encodedvideo}`. One video per request. <br> - Up to 8 images per request. <br>For `system` and `assistant` roles, the object list format is not supported.
messages[].nameoptionalOptional participant or tool name.
messages[].tool_call_idoptionalTool call ID that this tool message is responding to.
messages[].tool_callsoptionalTool calls generated by an assistant message.
messages[].reasoning_contentoptionalOptional preserved reasoning content from a previous assistant turn.
modelrequiredThe model to use.
minimaxai/minimax-m3.1-flashtoolsoptionalOptional OpenAI-compatible tool definitions for function calling.
max_tokensoptionalThe maximum number of tokens that can be generated.
16384seedoptionalChanging the seed will produce a different response with similar characteristics. Fixing the seed will reproduce the same results if all other parameters are also kept constant.
0streamoptionalIf set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]`
truestream_optionsoptionalOptional OpenAI-compatible stream options, such as `include_usage`.
temperatureoptionalWhat sampling temperature to use, between 0 and 2. Higher values make the output more random; lower values make it more focused and deterministic. Recommended for MiniMax-M3.1-Flash: 1.0, with top_p 0.95.
1top_poptionalNucleus sampling: only the tokens comprising the top_p probability mass are considered. Recommended for MiniMax-M3.1-Flash: 0.95.
0.95Headers3 Headers
AuthorizationrequiredFormat: Bearer $NVIDIA_API_KEY
Content-TyperequiredAcceptoptional