Skip to navigation
API Reference

Vqa

View as Markdown

Request

This endpoint expects an object.
messageslist of objectsRequired
modelstringOptionalDefaults to nvidia/alpamayo1.5
max_tokensintegerOptional1-1024Defaults to 256
temperaturedoubleOptional0-2Defaults to 0.6
top_pdoubleOptional0-1Defaults to 0.98
top_kinteger or nullOptional1-2147483647
seedinteger or nullOptional0-2147483647

Optional per-request sampling seed. When omitted, the container default seed is used. For repeatable K=1 trajectory inference in the same deployment, use a fixed seed with top_k=1 and top_p=1.

streambooleanOptionalDefaults to false
nvextobject or nullOptional

Response

Successful Response
idstring
createdinteger
modelstring
questionstring
answerstring
object"vqa.response"OptionalDefaults to vqa.response
inference_timedouble or nullOptional

Errors

422
Unprocessable Entity Error