Speka
Start free
All models
embeddingNVIDIA

Llama Nemotron Embed 1B v2

Current-generation NVIDIA retrieval embedding model — 2048-dimension vectors tuned for multilingual RAG.

nvidia/llama-nemotron-embed-1b-v2
Running· verified just now · 133ms

What is Llama Nemotron Embed 1B v2?

Llama Nemotron Embed 1B v2 is NVIDIA's embedding model. Current-generation NVIDIA retrieval embedding model — 2048-dimension vectors tuned for multilingual RAG. It runs on Speka's OpenAI-compatible /v1/embeddings endpoint at $0.012 per 1M input tokens, using the model ID nvidia/llama-nemotron-embed-1b-v2.

Test it live

Live playgroundLlama Nemotron Embed 1B v2in-browser demo

Embed text with Llama Nemotron Embed 1B v2

Enter text to see a vector preview.

How to call Llama Nemotron Embed 1B v2 via the API

Speka exposes Llama Nemotron Embed 1B v2 on an OpenAI-compatible /v1/embeddings endpoint. Point any OpenAI SDK at https://speka.me/v1, set model to nvidia/llama-nemotron-embed-1b-v2, and your existing code runs unchanged.

quickstart.py
from openai import OpenAI

client = OpenAI(
    base_url="https://speka.me/v1",
    api_key="sk-speka-live-...",  # your Speka key
)

resp = client.embeddings.create(
    model="nvidia/llama-nemotron-embed-1b-v2",
    input=["The quick brown fox"],
)
print(resp.data[0].embedding[:8])
FAQ

Frequently asked questions

Llama Nemotron Embed 1B v2 is NVIDIA's embedding model. Current-generation NVIDIA retrieval embedding model — 2048-dimension vectors tuned for multilingual RAG. It is available on Speka's OpenAI-compatible API using the model ID nvidia/llama-nemotron-embed-1b-v2.
On Speka, Llama Nemotron Embed 1B v2 is priced at $0.012 per 1M input tokens. Pricing is per-token with no subscription or seat fee — usage is billed against your plan's monthly allowance, then at the same rate with no overage penalty. Rates are current as of June 2026; check the pricing page for updates.
Speka exposes Llama Nemotron Embed 1B v2 on an OpenAI-compatible /v1/embeddings endpoint. Set base_url to https://speka.me/v1, supply your Speka key, and set model to "nvidia/llama-nemotron-embed-1b-v2" in any OpenAI SDK — no other code changes are required.
Llama Nemotron Embed 1B v2 supports a 8,192-token context window — roughly 6,000 words of input, suitable for long documents, multi-turn agents, and large-context tasks.
Yes. Llama Nemotron Embed 1B v2 is served through Speka's OpenAI-compatible endpoint, so any application built on the OpenAI Python or Node.js SDK, LangChain, or LlamaIndex can call it by changing only the base URL and model ID.

More embedding models

NVIDIA logo

NV-EmbedQA E5 v5

NVIDIA
embedding

Robust retrieval embeddings tuned for question answering and RAG pipelines.

nvidia/nv-embedqa-e5-v5
Input / 1M
$0.01
Open model
NVIDIA logo

Nemotron 3 Embed 1B

NVIDIA
embedding

Nemotron 3 embedding model for semantic search, clustering and reranking-style similarity scoring.

nvidia/nemotron-3-embed-1b
Input / 1M
$0.012
Open model
NVIDIA logo

NV-Embed v1

NVIDIA
embedding

High-accuracy general-purpose text embeddings for semantic search and clustering.

nvidia/nv-embed-v1
Input / 1M
$0.016
Open model