nvidia

NVIDIA: Nemotron 3.5 Super VL (free)

Quality Score
100/100
price + capability + benchmarks
Input Price
Free
per 1M tokens · checked 2026-11-08
Output Price
Free
per 1M tokens · checked 2026-11-08
Context Window
1,000,000
tokens

Nemotron 3.5 Super VL (free) is an NVIDIA model that accepts text, image, and video input and returns text. It offers a 1,000,000-token context window and can generate up to 131,072 tokens in a single completion, which suits long documents, extended transcripts, or large multimodal inputs. It supports tool calling and reasoning. Structured output support is not documented in the available listing, so verify it before relying on schema-constrained responses. The main reason to shortlist this model is cost: input and output are both priced at zero, making it a practical option for prototyping, high-volume experiments, or video and image workflows where paid multimodal models would add up quickly. The tradeoff is that it has no independent benchmark coverage yet, so its quality relative to other models is unproven. Teams should run their own evaluations on representative tasks before committing it to production workloads.

Model ID
nvidia/nemotron-3.5-super-vl:free
Vendor
nvidia
Released
October 2026
Tokenizer
Other
Input Modalities
text, image, video
Output Modalities
text
Max Output
131,072 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

Strong choice for

Category rankings

Where NVIDIA: Nemotron 3.5 Super VL (free) places across the 6 categories it ranks in. How we rank →

#CategoryScore
#2 Cheap Bulk InferenceCost · of 25 ranked 138
#2 Self-Hosted / LocalCost · of 25 ranked 118
#4 Social Media PostsWriting · of 25 ranked 120
#4 Voice Assistant BackendVoice · of 25 ranked 124
#4 Real-Time ChatLatency · of 25 ranked 118
#6 Video Auto-TaggingVideo · of 25 ranked 123

Similar models

Quick answers

Is NVIDIA: Nemotron 3.5 Super VL (free) free to use?
Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
What is NVIDIA: Nemotron 3.5 Super VL (free)'s context window?
1,000,000 tokens, roughly 1,500 pages of text in a single request.
Does NVIDIA: Nemotron 3.5 Super VL (free) support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can NVIDIA: Nemotron 3.5 Super VL (free) process images?
Yes, it accepts image input.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.