Skip to content
Apertis

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 Super (Free)NVIDIARemove
  2. Perceptron Mk1.5PerceptronRemove
  3. Universal-3.5 ProAssemblyAIRemove
nemotron-3-super-120b-a12b:free vs perceptron-mk1.5 vs universal-3-5-pro
AttributeNemotron 3 Super (Free)nemotron-3-super-120b-a12b:freePerceptron Mk1.5perceptron-mk1.5Universal-3.5 Prouniversal-3-5-pro
Pricing
Input$0 / 1M$0.15 / 1M— Not priced per input token
Output$0 / 1M$1.50 / 1M— Not priced per output token
Cache Write$0 / 1M——
Cache Read$0 / 1M$0.15 / 1MNot applicable
Cache Write (5m)—$0.15 / 1MNot applicable
Cache Write (1h)—$0.15 / 1MNot applicable
Web Search—$0 / 1M$0 / 1M
Context
Max context262.1K36.9KN/A
Max outputN/AN/AN/A
Capabilities
VisionYesNoNo
Function CallingYesNoNo
JSON ModeYesNoNo
StreamingYesYesNo
Catalogue
ProviderNVIDIAPerceptronAssemblyAI
Categorychatchatvoice
Charge typeFreePay As You GoPay As You Go
Released—2026-09-252026-09-22
Description
SummaryNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid Mixture-of-Experts model designed for complex multi-agent and long-horizon reasoning workflows. It activates only 12B parameters per token, enabling high compute efficiency while maintaining strong accuracy on advanced tasks. Built on a hybrid Mamba–Transformer MoE architecture with multi-token prediction (MTP), the model delivers significantly higher token generation throughput than leading open models. It supports a 1M-token context window for long-context reasoning, cross-document analysis, and multi-step task planning. Trained with multi-environment reinforcement learning across diverse benchmarks—including AIME 2025, TerminalBench, and SWE-Bench Verified—Nemotron 3 Super achieves strong performance across reasoning and coding tasks. Released fully open with weights, datasets, and training recipes, it supports flexible customization and secure deployment from local workstations to cloud environments.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.AssemblyAI Universal-3.5 Pro speech-to-text. Billed per second of audio.