API Reference

Request response from the model

post
https://integrate.api.nvidia.com/v1/chat/completions

Invokes inference using the model chat parameters.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params
messages
array of objects
required
length ≥ 1

A list of messages comprising the conversation so far.

Messages*
string
enum
required

The role of the message's author.

Allowed:
string | array
required

The contents of the message.

To pass media (only with role=user):

- Use content parts. Text is passed with type=text.

- 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}.

- Videos use type=video_url; audios use type=audio_url or type=input_audio when supported by the model schema.

For system and assistant roles, the object list format is not supported.

string
required
Defaults to nvidia/nemotron-3-nano-omni-30b-a3b-reasoning

The model to use.

1 to 65536

The maximum number of tokens that can be generated.

integer
-1 to 32768
Defaults to 16384

Maximum number of tokens the model is allowed to use for internal reasoning before the reasoning trace is forced to end. Use -1 to disable budget enforcement. This can also be provided via chat_template_kwargs.reasoning_budget for backwards compatibility.

-9223372036854776000 to 9223372036854776000

Changing 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.

If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE]

0 to 2

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

≤ 1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Headers
string
enum
Defaults to application/json

Generated from available response content types

Allowed:
Responses

Updated about 16 hours ago

Did this page help you?
Language
Credentials
Bearer
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json
text/event-stream

Updated about 16 hours ago

Did this page help you?
country_code