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. Perceptron Mk1.5PerceptronRemove
  3. Qwen3.8 2.4T A95BAlibabaRemove
nemotron-3.5-super-vl:free vs perceptron-mk1.5 vs qwen3.8-2.4t-a95b
AttributeNemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:freePerceptron Mk1.5perceptron-mk1.5Qwen3.8 2.4T A95Bqwen3.8-2.4t-a95b
Pricing
Input$0 / 1M$0.15 / 1M$1.80 / 1M
Output$0 / 1M$1.50 / 1M$5.40 / 1M
Cache Write$0 / 1M——
Cache Read$0 / 1M$0.15 / 1M$1.80 / 1M
Cache Write (5m)—$0.15 / 1M$1.80 / 1M
Cache Write (1h)—$0.15 / 1M$1.80 / 1M
Web Search—$0 / 1M$0 / 1M
Context
Max context1M36.9K262K
Max outputN/AN/AN/A
Capabilities
VisionYesNoYes
Function CallingYesNoYes
JSON ModeYesNoYes
StreamingYesYesYes
Catalogue
ProviderNVIDIAPerceptronAlibaba
Categorychatchatchat
Charge typeFreePay As You GoPay 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.Perceptron Mk1.5 chat model that accepts audio input. Audio and text input are billed per token.Qwen3.8 2.4T A95B is Qwen's open-weight sparse Mixture-of-Experts (MoE) model and the open-weight counterpart to Qwen3.8 Max. It features 2.4T total parameters with 95B activated per token, combining frontier-scale capacity with efficient sparse inference. Designed for coding, research, complex reasoning, and agentic workflows, the model is well suited for demanding long-horizon tasks and advanced autonomous systems while providing the flexibility and customization benefits of open weights.