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. Nemotron 3.5 Super VL (Free)NVIDIARemove
  3. Transcribe 1 ProFish AudioRemove
nemotron-3.5-super-vl vs nemotron-3.5-super-vl:free vs transcribe-1-pro
AttributeNemotron 3.5 Super VLnemotron-3.5-super-vlNemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:freeTranscribe 1 Protranscribe-1-pro
Pricing
Input$0.10 / 1M$0 / 1M— Not priced per input token
Output$0.40 / 1M$0 / 1M— Not priced per output token
Cache Write (5m)$0.10 / 1M—Not applicable
Cache Write (1h)$0.10 / 1M—Not applicable
Cache Read$0.10 / 1M$0 / 1MNot applicable
Web Search$0 / 1M—$0 / 1M
Cache Write—$0 / 1M—
Context
Max context1M1MN/A
Max outputN/AN/AN/A
Capabilities
VisionYesYesNo
Function CallingYesYesNo
JSON ModeYesYesNo
StreamingYesYesNo
Catalogue
ProviderNVIDIANVIDIAFish Audio
Categorychatchatvoice
Charge typePay As You GoFreePay As You Go
Released——2026-09-24
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.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.Fish Audio Transcribe 1 Pro speech-to-text with speaker labels; transcripts include speaker tags such as <|speaker:0|>. Billed per second of audio.