# Nemotron 3.5 Super VL

> Source: TokenPricing (https://tokenpricing.co) — https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl. When citing or reusing this content, credit "TokenPricing" and link to https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl.

比较 9 家服务商 的 Nemotron 3.5 Super VL API 价格。输入价从每百万 token $0.09 起，并列出输出、缓存、其他已公布费用、速度和可用率。

Canonical URL: https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl
Last updated: 2026-10-18

Reproduction and quotation must name TokenPricing, link to the canonical HTML URL, and retain individual source citations.

Price interpretation: a displayed $0.00 is a reported zero rate, not a missing price or a promise of unlimited free access; provider eligibility, availability and limits still apply. Missing prices are marked unavailable.

[计算](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Aio-net%2Fnvfp4)

工具调用推理缓存结构化输出

最低输入价

$0.09

Io Net

上下文

1M

## 比较服务商

每个点是一家服务商。从左到右是每百万 token 的输入价，从下到上是输出价。

## 基础价格

9

最新价格检查于 Nov 18, 2026。

|  |  |  |  |  |  |  |
| --- | --- | --- | --- | --- | --- | --- |
| Nebiusfp4 | $0.30 | $0.90 | $0.06 | $0.36 | 100% | [用 Nebius 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Anebius%2Ffp4) |
| BaseTenfp4 | $0.20 | $0.50 | $0.04 | $0.215 | 100% | [用 BaseTen 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Abaseten%2Ffp4) |
| Venicefp4 | $0.20 | $0.50 | $0.04 | $0.215 | 99.6% | [用 Venice 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Avenice%2Ffp4) |
| DeepInfrafp4 | $0.15 | $0.50 | $0.02 | $0.1888 | 99.9% | [用 DeepInfra 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Adeepinfra%2Ffp4) |
| PRPrimeIntellectnvfp4 | $0.15 | $0.50 | $0.02 | $0.1888 | 98.2% | [用 PrimeIntellect 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Aprimeintellect%2Fnvfp4) |
| Together | $0.15 | $0.50 | $0.02 | $0.1888 | 100% | [用 Together 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Atogether) |
| COCoreWeavenvfp4 | $0.15 | $0.47 | $0.02 | $0.1813 | 98.5% | [用 CoreWeave 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Acoreweave%2Fnvfp4) |
| Crusoebf16 | $0.10 | $0.40 | $0.08 | $0.1675 | 98.1% | [用 Crusoe 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Acrusoe%2Fbf16) |
| Io Netnvfp4 | $0.09 | $0.30 | $0.012 | $0.1132 | 97.0% | [用 Io Net 计算 Nemotron 3.5 Super VL](https://tokenpricing.co/zh/calculator?model=openrouter%3Anvidia%2Fnemotron-3.5-super-vl%3Aio-net%2Fnvfp4) |

## Nemotron 3.5 Super VL · 已公布价格

| Billing category | Input / 1M | Output / 1M | Cache read / 1M |
| --- | --- | --- | --- |
| NVIDIA hosted trial | No paid tariff published | No paid tariff published | Not reported |
| OpenRouter NVIDIA :free | $0 | $0 | Not reported |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)[[3]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-3)

## Nemotron 3.5 Super VL · 权重许可证

| 模型权重 | 协议 |
| --- | --- |
| 开放权重 | OpenMDW 1.1 |

[[1]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-1)

## Nemotron 3.5 Super VL · 权重与量化

| Item | Configuration / evidence |
| --- | --- |
| Checkpoint | Nemotron 3.5 Super VL 120B-A12B NVFP4; OpenMDW 1.1 |
| Quantization | W4A4 on Blackwell; W4A16 on non-Blackwell, per serving configuration |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## Nemotron 3.5 Super VL · 自部署硬件

| Item | Configuration / evidence |
| --- | --- |
| Supported hardware | Blackwell GB200 / DGX Spark; Hopper H100 / H200 |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## Nemotron 3.5 Super VL · 部署方式

| Item | Configuration / evidence |
| --- | --- |
| Serving engines | vLLM / SGLang; NVIDIA GPU-accelerated systems |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## Nemotron 3.5 Super VL · 上下文与渠道限制

| Item | Configuration / evidence |
| --- | --- |
| Local context | Up to 1M; recipes may reduce context for GPU memory and concurrency |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## Nemotron 3.5 Super VL · 已知风险与限制

| Item | Configuration / evidence |
| --- | --- |
| Benchmark scope | NVIDIA evaluations use NeMo Gym recipes; not independent LMSpeed measurements |
| Model identity | This is Super VL 120B-A12B; no BOLT variant or edge latency result verified |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## Nemotron 3.5 Super VL · 使用场景

| Item | Configuration / evidence |
| --- | --- |
| Enterprise use cases | Document and video understanding; coding, reasoning and tool-using agents |

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

## 上下文与限制

- It does not publish a paid per-token tariff.

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)[[3]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-3)

- NVIDIA Nemotron **3.5** Super VL has **120** billion total parameters and **12** billion active parameters.

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

- The model card currently describes the NVFP4 quantized release.

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)

- Use of the model is governed by the OpenMDW License Agreement version **1.1**.

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)[[3]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-3)

- Access to the hosted trial is governed by the NVIDIA API Trial Terms of Service.

[[2]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-2)[[3]](https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl#model-source-3)

## 其他模型

打开另一个当前模型，比较它的服务商。

[Nemotron 3.5 Transcribe](https://tokenpricing.co/zh/nvidia/nemotron-3.5-transcribe)

Nemotron 3.5 Transcribe

NVIDIA

[GPT-6.2 Astra](https://tokenpricing.co/zh/openai/gpt-6-2-astra)

GPT-6.2 Astra

OpenAI

[GPT-6.2 Sol](https://tokenpricing.co/zh/openai/gpt-6-2-sol)

GPT-6.2 Sol

OpenAI

[Seedance 2.5 Flash](https://tokenpricing.co/zh/bytedance/seedance-2.5-flash)

Seedance 2.5 Flash

ByteDance

[MAI-Image-2.7](https://tokenpricing.co/zh/microsoft/mai-image-2.7)

MAI-Image-2.7

Microsoft

[Microsoft-Decision-1.1](https://tokenpricing.co/zh/microsoft/microsoft-decision-1-1)

Microsoft-Decision-1.1

Microsoft

## 关于 Nemotron 3.5 Super VL

## 来源与注脚

- [1]

[来源](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4)核验日期： 2026-10-18

- [2]

[NVIDIA model card and trial terms · NVIDIA official model card](https://build.nvidia.com/nvidia/nemotron-3.5-super-vl-120b-a12b/modelcard)核验日期： 2026-10-16, 2026-10-17

- [3]

[OpenRouter NVIDIA free endpoint](https://openrouter.ai/nvidia/nemotron-3.5-super-vl:free)核验日期： 2026-10-16

输入、输出和缓存读取的单位是每百万 token 的美元价格。速度是每秒输出 token 数。可用率是来源报告的在线比例。

---
Cite as: Nemotron 3.5 Super VL — TokenPricing, https://tokenpricing.co/zh/nvidia/nemotron-3.5-super-vl (retrieved 2026-11-19)
