Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Nemotron 3.5 Super VL (Free)NVIDIARemove
  2. BGE Reranker V2 M3RerankerRemove
nemotron-3.5-super-vl:free vs BAAI/bge-reranker-v2-m3
AttributeNemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:freeBGE Reranker V2 M3BAAI/bge-reranker-v2-m3
Pricing
Input$0 / 1M$0.14 / 1M
Output$0 / 1M$0.14 / 1M
Cache Write$0 / 1M—
Cache Read$0 / 1MNot applicable
Cache Write (5m)—Not applicable
Cache Write (1h)—Not applicable
Web Search—$0 / 1M
Context
Max context1M8.2K
Max outputN/AN/A
Capabilities
VisionYesNo
Function CallingYesNo
JSON ModeYesNo
StreamingYesNo
Catalogue
ProviderNVIDIAReranker
Categorychatchat
Charge typeFreePay As You Go
Released——
Description
SummaryNVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications.—