Skip to content
nvidia/nemotron-3-embed-1b

33K context · Jul 2026 · 2 upstreams

NVIDIA Nemotron-3-Embed-1B is a 1.14B-parameter multilingual text embedding model (2048 dimensions, 34 languages) for semantic search, retrieval, and RAG. Built on Ministral-3-3B-Instruct; state-of-the-art on multilingual retrieval benchmarks (MMTEB 71.05, RTEB 72.38). Served via NVIDIA NIM.

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

Upstreams

2
  1. 1NVIDIAPlatform · freeFreeTPS —TTFT ——
  2. 2NVIDIAYour key · not addedyour planTPS —TTFT ——

Try it

Embed a sentence

Uptime, last 48 hours

No health checks yet.

  • Up
  • No traffic
  • Down

Details

Owner
NVIDIA
Kind
Embeddings
Released
Jul 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-embed-1b",
    "input": "The quick brown fox jumps over the lazy dog"
  }'