AI Models Directory
Nvidia
Llama Nemotron Embed VL 1B V2 (free)
A fast decision page for teams comparing performance, cost, context window, and critical capabilities without digging through raw specs.
ELO
—
nDCG@10
—
Latency
—
Input $/M
$0.000
Quick signals
- Provider: Nvidia
- Inputs: text, image
- Latest update: 2026-02-25
Usage profile
- Context window: 131K
- Max output: —
- Open weights: No
License & usage
- License
- —
- Open Source
- No
- Price / 1M
- $0.000
- Max Context (In)
- 131K
- Model type
- Embedding