llama-text-embed-v2
llama-text-embed-v2 is a text embedding model built by NVIDIA on the Llama 3.2 1B architecture, converting text into dense vectors for semantic search and retrieval across 26 languages.
text → embedding · made by NVIDIA
$0.16per Mtok in
Pinecone
Sold by 1 way
| Seller | Lane | Rate |
|---|---|---|
| Pinecone cloud | standard | $0.16per Mtok inpinecone.io · read 2026-08-25 |
About
llama-text-embed-v2 — a vectors model from NVIDIA, sold by one company from $0.16 per Mtok in.
It takes text and returns vectors, with a context window of 2,048 tokens. The catalogue files it under embedding. Only Pinecone sells it, at $0.16 per Mtok in.
Every current figure
- Maker
- NVIDIA
- Register
- model
- Takes
- text
- Returns
- embedding
- Context
- 2,048 tokens
- Sellers
- 1
- Maker's own price
- not read
- Price
- $0.16 per Mtok in — Pinecone