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. Whisper Large V3OpenAIRemove
  3. Nemotron 3.5 Super VLNVIDIARemove
nemotron-3.5-super-vl:free vs whisper-large-v3 vs nemotron-3.5-super-vl
AttributeNemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:freeWhisper Large V3whisper-large-v3Nemotron 3.5 Super VLnemotron-3.5-super-vl
Pricing
Input$0 / 1M$9.25 / 1M$0.10 / 1M
Output$0 / 1M— Not priced per output token$0.40 / 1M
Cache Write$0 / 1M——
Cache Read$0 / 1MNot applicable$0.10 / 1M
Cache Write (5m)—Not applicable$0.10 / 1M
Cache Write (1h)—Not applicable$0.10 / 1M
Web Search—$0 / 1M$0 / 1M
Context
Max context1MN/A1M
Max outputN/AN/AN/A
Capabilities
VisionYesNoYes
Function CallingYesNoYes
JSON ModeYesYesYes
StreamingYesNoYes
Catalogue
ProviderNVIDIAOpenAINVIDIA
Categorychatvoicechat
Charge typeFreePay 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.Whisper Large V3 is OpenAI's advanced open-source automatic speech recognition (ASR) model, supporting both audio transcription and translation across 99+ languages. It accepts common audio formats including mp3, mp4, wav, webm, flac, and ogg, and delivers strong performance in noisy, real-world conditions. With 1.55B parameters and a low 10.3% word error rate, it provides accurate, multilingual transcription with support for word- and segment-level timestamps, making it well suited for high-quality, noise-robust speech processing applications.NVIDIA 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.