Model
Llama Nemotron Embed VL 1B v2
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
1 providersreleased open weights
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Nvidia nvidia/llama-nemotron-embed-vl-1b-v2 | — | — | — | — | 33K | no reasoningno toolsno structuredvision | Feb 10, 2026 |
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.