Nemotron-3.5-Embed-1B-BF16 · deepinfra

Nemotron-3.5-Embed-1B-BF16 is a compact multimodal embedding model from NVIDIA that maps text, images, and page screenshots into a shared 2048-dimensional vector space for visual document retrieval and semantic search. It pairs the Nemotron-3-Embed-1B text encoder with a vision encoder, supports up to 32k tokens and Matryoshka dimensions, and suits multilingual RAG over PDFs, slides, and scanned documents.

Base modelAll models on this baseAll models of the providerto the provider

All NVIDIA models at every provider

Input, $/1M $0.015

Output, $/1M —

Context 32 768

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —