AI Models Directory
Nvidia
Open Source
llama-nemotron-rerank-vl-1b-v2
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
—
Quick signals
- Provider: Nvidia
- Inputs: text, image
- Latest update: 2026-03-31
Usage profile
- Context window: 128K
- Max output: —
- Open weights: Yes
License & usage
- License
- Open Source
- Open Source
- Yes
- Price per 1K queries
- $0.000
- Max Context (In)
- 128K
- Model type
- Rerank