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. Qwen3 Next 80B A3B ThinkingAlibabaRemove
nemotron-3.5-super-vl:free vs qwen3-next-80b-a3b-thinking
AttributeNemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:freeQwen3 Next 80B A3B Thinkingqwen3-next-80b-a3b-thinking
Pricing
Input$0 / 1M$0.10 / 1M
Output$0 / 1M$0.40 / 1M
Cache Write$0 / 1M—
Cache Read$0 / 1M$0.10 / 1M
Cache Write (5m)—$0.10 / 1M
Cache Write (1h)—$0.10 / 1M
Web Search—$0 / 1M
Context
Max context1M262.1K
Max outputN/AN/A
Capabilities
VisionYesNo
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderNVIDIAAlibaba
Categorychatchat
Charge typeFreePay 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.Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model designed for difficult multi-step tasks such as math proofs, code synthesis and debugging, logical reasoning, and agentic planning. It outputs structured thinking traces by default, emphasizing stability over long chains of thought, efficient inference scaling, and strong instruction following. Suited for agent frameworks, tool use, retrieval-heavy workflows, and benchmarks requiring step-by-step solutions, it supports long detailed outputs and faster generation via throughput-optimized techniques, operating exclusively in thinking mode.