NVIDIA: Nemotron 3.5 Super VL (free)

Image input Video input Text input Text output
Author's Description

NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

Key Specifications
Cost
$$$$
Context
262K
Parameters
120B (Rumoured)
Released
Oct 15, 2026
Speed
★★
Ability
★★★
Reliability
★★
Supported Parameters

This model supports the following parameters:

Logit Bias Tools Top P Reasoning Min P Stop Structured Outputs Logprobs Response Format Top Logprobs Max Tokens Tool Choice Frequency Penalty Presence Penalty Include Reasoning Temperature
Features

This model supports the following features:

Structured Outputs Response Format Reasoning Tools
Performance Summary

NVIDIA Nemotron 3.5 Super VL demonstrates a balanced performance profile, excelling in reliability and specific accuracy benchmarks while maintaining competitive pricing. Its speed performance is moderate, ranking in the 39th percentile across benchmarks. The model offers competitive pricing, placing in the 45th percentile. A standout feature is its exceptional reliability, boasting a 98% success rate, indicating minimal technical failures and consistent evaluable responses. In terms of accuracy, Nemotron 3.5 Super VL shows remarkable strength in Mathematics, achieving 97.0% accuracy (95th percentile), and strong performance in Coding with 93.0% accuracy (72nd percentile). Instruction Following is also robust at 80.0% accuracy (81st percentile). Its primary area for improvement lies in Reasoning, where it achieved 76.0% accuracy (46th percentile), suggesting it performs around the median for complex logical tasks. While durations for individual benchmarks vary, the overall speed ranking indicates it is not among the fastest models. Its multimodal capabilities, handling text, images, documents, GUI screenshots, and video, position it as a versatile tool despite its moderate speed.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.15
Completion $0.5
Input Cache Read $0.02

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Together
Together | nvidia/nemotron-3.5-super-vl-20261015 262K $0.15 / 1M tokens $0.5 / 1M tokens
DeepInfra
DeepInfra | nvidia/nemotron-3.5-super-vl-20261015 262K $0.2 / 1M tokens $1 / 1M tokens
CoreWeave
CoreWeave | nvidia/nemotron-3.5-super-vl-20261015 1M $0.25 / 1M tokens $1.5 / 1M tokens
Crusoe
Crusoe | nvidia/nemotron-3.5-super-vl-20261015 262K $0.1 / 1M tokens $0.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by nvidia