Nemotron 3 Embed 1B
Small open embedding model for high-throughput enterprise retrieval.
NVIDIA Nemotron 3 Embed 1B is an open text embedding model optimised for high-throughput, low-latency retrieval — enterprise search, RAG, code retrieval and agentic retrieval.
- Provider
- NVIDIA
- Type
- Embedding model
- Released
- Jul 16, 2026
- Context window
- 33K tokens
- Price
- Free tier on OpenRouter
- Input
- text
- Output
- embedding
- Open weights
- Yes
Best for
- High volume / low cost
- Enterprise
- Local & on-device
Strengths
- 1B parameters — cheap to self-host
- 32K-token inputs
- Free on OpenRouter
More from NVIDIA
- Nemotron 3 Super — NVIDIA. Open hybrid Mamba-Transformer MoE for multi-agent applications.
- Nemotron 3.5 Lightning — NVIDIA. Tiny open 30B-A3B model with the lowest first-token latency in the index.
- Nemotron 3 Ultra — NVIDIA. NVIDIA’s largest open model: hybrid Mamba-Transformer MoE, 55B active.
- Cosmos 3 — NVIDIA. NVIDIA’s open omni-modal world foundation model for physical AI.
- Isaac GR00T N1.7 — NVIDIA. Open 3B cross-embodiment VLA for humanoids and manipulators.
- Nemotron 3.5 Content Safety — NVIDIA. Compact 4B multimodal guardrail model for LLM and VLM traffic.