Skip to content
AnyRouter

Nemotron 3.5 Embed 1B

Free
nvidia/nemotron-3.5-embed-1b

33K context · Oct 2026 · 2 upstreams

NVIDIA Nemotron 3.5 Embed 1B is a 1.55B-parameter multimodal and multilingual retrieval embedding model. It embeds text (34 evaluated languages) and, on the model card, document-page images, into one 2048-dimension vector for semantic search and RAG; vectors can be truncated and re-normalized. 32,768-token context. On AnyRouter's embeddings endpoint the input is text. It was distilled from the 8B model and shares the text embedding space of Nemotron 3 Embed 1B.

max input
33K
dimensions
—
input / 1M
$0
routes
2

Upstreams

2
  1. 1NVIDIAPlatform · freeFreeTPS —TTFT ——
  2. 2NVIDIAYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Embed a sentence

Details

Owner
NVIDIA
Kind
Embeddings
Released
Oct 2026
Context
33K
Data policy
Provider retention
Endpoint
/api/v1/embeddings

Quick start

curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-embed-1b",
    "input": "The quick brown fox jumps over the lazy dog"
  }'