D
Llama Nemotron Rerank VL 1B v2
Llama Nemotron Rerank VL 1B v2, a reranking model from DeepInfra.
model: "llama-nemotron-rerank-vl-1b-v2-deepinfra"
Nvidia·served via
DeepInfra·Released March 2026Pricing
- Per 1M tokens
- $0.010 / 1M
Specifications
- Context window
- 10,240 tokens
- Max documents
- 1,000
- Max document tokens
- 10,240
- Released
- March 2026
- Model string
- nvidia/llama-nemotron-rerank-vl-1b-v2
Use this model
// Reranking runs inside vector search, reordering results // by relevance. Selected in the corpus configuration. // Model id: 0