Nvidia Nemotron 3.5 Super VL
by NanoGPT · family nemotron · listed Oct 2026RTVW
NVIDIA’s open-weight 120B model (12B active) for reasoning, coding, tool use, document and GUI understanding, and video understanding. Text, images and video in; text out. Served in NVFP4 with a 262,144-token shared context window. NanoGPT currently limits responses to 16,384 tokens while separate hosted output limits remain unpublished. OpenMDW 1.1 license.
Current rates USD per 1M tokens
Input$0.15
Output$0.50
Cache read$0.02
Cache write—
Against the market
On the record
- Model id
nvidia/nemotron-3.5-super-vl- Context window
- 262K tokens
- Max output
- 16K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-10-15
- Last updated
- 2026-10-15
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.06 in · $0.35 out
- OpenRouter$0.15 in · $0.47 out
- Vercel AI Gateway$0.20 in · $0.50 out
- CommandCode$0.20 in · $0.50 out
- CheapestToken$0.30 in · $0.65 out
- DigitalOcean$0.30 in · $0.65 out
- Nebius Token Factory$0.30 in · $0.90 out