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. Hy4 previewTencentRemove
  3. mai-ds-r1:freeNot in the catalogueRemove
  4. Perceptron Mk1.5PerceptronRemove

4 is the maximum. Remove one to add another.

nemotron-3.5-super-vl vs hy4-preview vs mai-ds-r1:free vs perceptron-mk1.5
AttributeNemotron 3.5 Super VLnemotron-3.5-super-vlHy4 previewhy4-previewmai-ds-r1:freeNot in the cataloguePerceptron Mk1.5perceptron-mk1.5
Pricing
Input$0.10 / 1M$0.834 / 1M—$0.15 / 1M
Output$0.40 / 1M$2.50 / 1M—$1.50 / 1M
Cache Write (5m)$0.10 / 1M$0.834 / 1M—$0.15 / 1M
Cache Write (1h)$0.10 / 1M$0.834 / 1M—$0.15 / 1M
Cache Read$0.10 / 1M$0.834 / 1M—$0.15 / 1M
Web Search$0 / 1M$0 / 1M—$0 / 1M
Context
Max context1M1M—36.9K
Max outputN/AN/A—N/A
Capabilities
VisionYesYes—No
Function CallingYesYes—No
JSON ModeYesYes—No
StreamingYesYes—Yes
Catalogue
ProviderNVIDIATencent—Perceptron
Categorychatchat—chat
Charge typePay As You GoPay As You Go—Pay As You Go
Released———2026-09-25
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.Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world workflows.—Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.