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 VLNVIDIARemove
  2. Gemini Embedding 2GoogleRemove
  3. Gemini 4 CarbonGoogleRemove
nemotron-3.5-super-vl vs gemini-embedding-2-preview vs gemini-4-carbon
AttributeNemotron 3.5 Super VLnemotron-3.5-super-vlGemini Embedding 2gemini-embedding-2-previewGemini 4 Carbongemini-4-carbon
Pricing
Input$0.10 / 1M$0.60 / 1M$2.00 / 1M
Output$0.40 / 1M$2.40 / 1M$10.00 / 1M
Cache Write (5m)$0.10 / 1M$0.60 / 1M$2.00 / 1M
Cache Write (1h)$0.10 / 1M$0.60 / 1M$2.00 / 1M
Cache Read$0.10 / 1M$0.60 / 1M$2.00 / 1M
Web Search$0 / 1M—$0 / 1M
Context
Max context1M8.2K1M
Max outputN/AN/AN/A
Capabilities
VisionYesYesYes
Function CallingYesYesYes
JSON ModeYesNoYes
StreamingYesNoYes
Catalogue
ProviderNVIDIAGoogleGoogle
Categorychatembeddingchat
Charge typePay As You GoPay As You GoPay 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.Gemini Embedding 2 is Google's advanced text embedding model designed for high-accuracy semantic representation across large-scale retrieval and understanding tasks. It converts text into dense vector embeddings optimized for semantic search, retrieval-augmented generation (RAG), clustering, classification, and recommendation systems. Built for production use, it offers strong multilingual support, improved semantic similarity accuracy, and efficient embedding generation, making it well suited for large knowledge indexing pipelines and enterprise-scale retrieval applications.Gemini 4 Carbon is Google's frontier multimodal reasoning model, designed for advanced coding, agentic workflows, and complex multi-step problem solving. It supports text, image, audio, video, and file inputs, enabling integrated reasoning and analysis across diverse modalities. Optimized for long-horizon execution and demanding professional workloads, Gemini 4 Carbon supports up to 1M output tokens through continuation and configurable reasoning effort levels (low, medium, high) to balance reasoning depth, latency, and cost. It is well suited for autonomous agents, software engineering, multimodal analysis, and large-scale workflow automation.