The Orchestrator › Models › NVIDIA
NVIDIA: Nemotron 3.5 Super VL
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...
Specifications
| Provider | NVIDIA |
| Model ID | nvidia/nemotron-3.5-super-vl |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image + video → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-10-15 |
| Tracked since | 2026-11-14 |
| Popularity | #18 by usage · peak 8.1% spend share in an OpenRouter category |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | nvidia/nemotron-3.5-super-vl | $0.15 | $0.47 | 1.0M |
| free | OpenRouter | nvidia/nemotron-3.5-super-vl:free | Free | Free | 1M |
| standard | TrustedRouter | nvidia/nemotron-3.5-super-vl | $0.105 | $0.422 | 1.0M |
| standard | Vercel AI Gateway | nvidia/nemotron-3.5-super-vl | $0.2 | $0.5 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.2 | $0.5 | 1.0M |
| 2026-11-14 | $0.105 | $0.422 | 1.0M |
| 2026-11-14 | $0.15 | $0.47 | 1.0M |
Capabilities
Vision (image input)Video inputAgentic tool useStructured outputs1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p