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. Tongyi DeepResearch 30B A3BAlibabaRemove
  2. Nemotron 3.5 Super VLNVIDIARemove
tongyi-deepresearch-30b-a3b vs nemotron-3.5-super-vl
AttributeTongyi DeepResearch 30B A3Btongyi-deepresearch-30b-a3bNemotron 3.5 Super VLnemotron-3.5-super-vl
Pricing
Input$0.135 / 1M$0.10 / 1M
Output$0.675 / 1M$0.40 / 1M
Cache Write (5m)$0.135 / 1M$0.10 / 1M
Cache Write (1h)$0.135 / 1M$0.10 / 1M
Cache Read$0.135 / 1M$0.10 / 1M
Web Search$0 / 1M$0 / 1M
Context
Max context131.1K1M
Max outputN/AN/A
Capabilities
VisionNoYes
Function CallingYesYes
JSON ModeYesYes
StreamingYesYes
Catalogue
ProviderAlibabaNVIDIA
Categorychatchat
Charge typePay As You GoPay As You Go
Released——
Description
SummaryTongyi DeepResearch is a 30B-parameter agentic model (3B active per token) built for long-horizon, deep research and information-seeking tasks. It achieves state-of-the-art results on major agentic search and reasoning benchmarks, outperforming prior models in complex multi-step problem solving. Trained with a fully automated synthetic data pipeline and advanced on-policy RL, it supports ReAct workflows and a high-performance “Heavy” mode for test-time scaling, making it well suited for advanced research agents, tool use, and intensive inference workloads.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.