BuildLearnCommunity ModelsCheapestLong-contextOpen sourceImage modelsTrending How we score API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › nvidia › NVIDIA: Nemotron 3.5 Super VL

NVIDIA: Nemotron 3.5 Super VL — pricing & benchmarks

By nvidia · Updated 2026-11-01 · Open weightsReads imageslong-context / RAGreads images / documentscheap high-volumestep-by-step reasoningopen weights / self-hostable

NVIDIA: Nemotron 3.5 Super VL costs $0.15 per 1M input tokens and $0.5 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable, and is available through one OpenAI-compatible Appmo API key.
$0.15Input / 1M
$0.5Output / 1M
1MContext
38Buzz (0-100)

What NVIDIA: Nemotron 3.5 Super VL is used for

NVIDIA: Nemotron 3.5 Super VL is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable. Access it through one Appmo API key alongside 444 other models — Appmo's optimizer can route to it automatically when it is the best value for a request. Weights: huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL.

What people are saying (last 30 days)

Not enough posts yet to judge community sentiment. 4 Hacker News stories (11 points) · 21 new GitHub repos mentioning it. How we measure this.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"nvidia/nemotron-3.5-super-vl","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does NVIDIA: Nemotron 3.5 Super VL cost?
NVIDIA: Nemotron 3.5 Super VL costs $0.15 per 1M input tokens and $0.5 per 1M output tokens ($0.238 blended), as of 2026-11-01. Prices are expected to fall as competition increases.

What is NVIDIA: Nemotron 3.5 Super VL best for?
NVIDIA: Nemotron 3.5 Super VL is best suited for long-context / RAG, reads images / documents, cheap high-volume, step-by-step reasoning, open weights / self-hostable.

How do I use NVIDIA: Nemotron 3.5 Super VL?
Send requests to Appmo's OpenAI-compatible endpoint with model id "nvidia/nemotron-3.5-super-vl" and one API key — no separate provider account needed.

Is NVIDIA: Nemotron 3.5 Super VL open source?
Yes — its weights are public on Hugging Face (nvidia/NVIDIA-Nemotron-3.5-Super-VL).

Can NVIDIA: Nemotron 3.5 Super VL create images?
No. NVIDIA: Nemotron 3.5 Super VL can read and understand images, but it only writes text.