NVIDIA

•

Open weights model

•

Released 2025年10月

NVIDIA Nemotron Nano 12B v2 VL：智能、性能与价格分析

立即试用

可用服务商

Amazon Bedrock

冗长度

无

Intelligence Index 输出 token 数

NVIDIA Nemotron Nano 12B v2 VL (Reasoning)支持文本和图像输入，可输出文本，上下文窗口为 128k 个 token。

输入模态	支持：文本和图像
输出模态	支持：文本
上下文窗口	128k 约 192 页 A4 纸（12 号 Arial 字体）
总参数量	13.2B
许可证	Nvidia Open Model License
模型权重	Hugging Face

指标与同类别模型进行比较：

非推理模型 → 仅与其他非推理模型比较
推理模型 → 同时与推理和非推理模型比较
开放权重模型 → 仅与规模类别相同的其他开放权重模型比较：

微型：≤4B 个参数
小型：4B–40B 个参数
中型：40B–150B 个参数
大型：>150B 个参数

专有模型 → 与价格区间相同的专有模型和开放权重模型比较，采用输入/输出价格 3:1 的混合比例：

每 100 万 token <$0.15
每 100 万 token $0.15–$1
每 100 万 token >$1

智能

Artificial Analysis Intelligence Index · Higher is better

No publicly available API

每任务耗时

Inference time (minutes) per Intelligence Index task · Lower is better

No publicly available API

每任务成本

Weighted average cost (USD) per Intelligence Index task · Lower is better

No publicly available API

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode-AA 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Artificial Analysis Intelligence Index：开放权重与专有模型

Indicates whether the model weights are available. Models are labelled as 'Commercial Use Restricted' if commercial use is limited by conditions, and as 'Non-commercial' if the license prohibits commercial use.

Intelligence Index 与每项任务的成本

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

Pareto line

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

基准测试

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better

MMMU-Pro

Visual reasoning

While model intelligence generally translates across use cases, specific evaluations may be more relevant for certain use cases.

Openness Index

Artificial Analysis Openness Index：得分

Openness Index 以 0 至 100 的标准化评分衡量模型的开放程度（分数越高，越开放）

成本

每项 Intelligence Index 任务的成本

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

运行 Artificial Analysis Intelligence Index 的成本

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index

The cost to run the evaluations in the Artificial Analysis Intelligence Index, calculated using the model's input, cache hit, cache write, reasoning, and answer token prices and the number of tokens used across evaluations (excluding repeats).

价格：缓存命中、输入和输出

Price (USD per M Tokens)

Price per token for cached prompts (previously processed), typically offering a significant discount compared to regular input price, represented as USD per million tokens. The values shown here are the cache hit price; cache write and cache storage are billed separately and vary by provider — see "Cache pricing by provider" for detail.

性能

按每任务耗时（分钟）、输出速度（每秒 token 数）、首个答案 Token 延迟和首 Token 延迟（秒）衡量

Intelligence Index 每项任务耗时

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

输出速度

Output tokens divided by total request time, including time to first token · Higher is better

Output tokens, including reasoning tokens, received per second over a request's full duration, from sending the request to receiving the final token. The headline value averages each Performance v3 workload over the past 5 days, then averages the workloads.

首个答案 Token 延迟

收到首个答案 token 的秒数 · 包含推理模型的“思考”时间

Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.

上下文窗口

Context window: tokens limit · Higher is better

Larger context windows are relevant to RAG (Retrieval Augmented Generation) LLM workflows which typically involve reasoning and information retrieval of large amounts of data.

Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).

模型规模（仅开放权重模型）

模型规模：总参数量与活跃参数量

Comparison between total model parameters and parameters active during inference (billions)

The total number of trainable weights and biases in the model, expressed in billions. These parameters are learned during training and determine the model's ability to process and generate responses.

The number of parameters actually executed during each inference forward pass, expressed in billions. For Mixture of Experts (MoE) models, a routing mechanism selects a subset of experts per token, resulting in fewer active than total parameters. Dense models use all parameters, so active equals total.

NVIDIA 的更多发布

常见问题

关于 NVIDIA Nemotron Nano 12B v2 VL 的常见问题

NVIDIA Nemotron Nano 12B v2 VL 发布于 2025年10月28日。

NVIDIA Nemotron Nano 12B v2 VL 由 NVIDIA 开发。

NVIDIA Nemotron Nano 12B v2 VL 的首个答案 Token 延迟为 1.56 秒（non-reasoning）（基于提供该模型的各服务商中位数）。NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) 的首个答案 Token 延迟与其他规模相近的开放权重非推理模型相比优于平均水平（中位数：2.68 秒）。

NVIDIA Nemotron Nano 12B v2 VL 每 100 万输入 token 的价格为 $0.20（non-reasoning），每 100 万输出 token 的价格为 $0.60（non-reasoning）；基于提供该模型的各服务商中位数。NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) 的输入价格略高于平均水平（中位数：$0.13），输出价格略高于平均水平（中位数：$0.25）。

NVIDIA Nemotron Nano 12B v2 VL 每 100 万输入 token 的价格为 $0.20（non-reasoning），每 100 万输出 token 的价格为 $0.60（non-reasoning）（基于提供该模型的各服务商中位数）。按缓存命中/输入/输出为 7:2:1 的比例计算，混合价格为每 100 万 token $0.24（non-reasoning）。价格可能因服务商而异。比较服务商价格

是，NVIDIA Nemotron Nano 12B v2 VL (Reasoning) 是推理模型。它会在给出答案之前，通过扩展思考或思维链推理来解决复杂问题。否，NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) 不是推理模型。它不进行扩展的思维链推理，而是直接作答。

NVIDIA Nemotron Nano 12B v2 VL 支持文本和图像输入。

NVIDIA Nemotron Nano 12B v2 VL 支持文本输出。

是，NVIDIA Nemotron Nano 12B v2 VL 支持图像输入，可以分析、描述图像并回答有关图像的问题。

是，NVIDIA Nemotron Nano 12B v2 VL 是多模态模型，可以处理文本和图像输入并生成文本输出。

NVIDIA Nemotron Nano 12B v2 VL 的上下文窗口为 128k 个 token。这决定了模型在单次请求中可以处理多少文本和对话历史。

是，NVIDIA Nemotron Nano 12B v2 VL 是开放权重模型，其模型权重已公开，可供下载并自行托管。

NVIDIA Nemotron Nano 12B v2 VL 有 13.2B 参数。

NVIDIA Nemotron Nano 12B v2 VL 基于 Nvidia Open Model License 许可证发布，该许可证允许商业使用。查看许可证

是，可通过 1 家服务商的 API 使用 NVIDIA Nemotron Nano 12B v2 VL。比较 API 服务商

可通过 1 家 API 服务商使用 NVIDIA Nemotron Nano 12B v2 VL。比较服务商

NVIDIA Nemotron Nano 12B v2 VL：智能、性能与价格分析

模型摘要

冗长度

技术规格

此类别中有 144 个模型

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index：开放权重与专有模型

Artificial Analysis Intelligence Index

Open Weights

Intelligence Index 与每项任务的成本

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Evaluations

Intelligence Evaluation Relevance

Artificial Analysis Intelligence Index

Openness Index

Artificial Analysis Openness Index：得分

成本

每项 Intelligence Index 任务的成本

Cost per Intelligence Index Task

运行 Artificial Analysis Intelligence Index 的成本

Cost to Run Artificial Analysis Intelligence Index

价格：缓存命中、输入和输出

Cache Hit

性能

Intelligence Index 每项任务耗时

Time per Intelligence Index Task

Time Period

输出速度

End-to-End Output Speed

首个答案 Token 延迟

Time to First Answer Token

上下文窗口

上下文窗口

Context Window for RAG

Context Window

模型规模（仅开放权重模型）

模型规模：总参数量与活跃参数量

Total Parameters

Active Parameters at Inference Time

更多详情

NVIDIA 的更多发布

常见问题

NVIDIA Nemotron Nano 12B v2 VL 何时发布？

谁开发了 NVIDIA Nemotron Nano 12B v2 VL？

NVIDIA Nemotron Nano 12B v2 VL 的延迟是多少？

NVIDIA Nemotron Nano 12B v2 VL 的费用是多少？

NVIDIA Nemotron Nano 12B v2 VL API 的价格是多少？

NVIDIA Nemotron Nano 12B v2 VL 是推理模型吗？

NVIDIA Nemotron Nano 12B v2 VL 支持哪些输入模态？

NVIDIA Nemotron Nano 12B v2 VL 支持哪些输出模态？

NVIDIA Nemotron Nano 12B v2 VL 能处理图像吗？

NVIDIA Nemotron Nano 12B v2 VL 是多模态模型吗？

NVIDIA Nemotron Nano 12B v2 VL 的上下文窗口有多大？

NVIDIA Nemotron Nano 12B v2 VL 是开放权重模型吗？

NVIDIA Nemotron Nano 12B v2 VL 有多少个参数？

NVIDIA Nemotron Nano 12B v2 VL 使用什么许可证？

可以通过 API 使用 NVIDIA Nemotron Nano 12B v2 VL 吗？

可以在哪里使用 NVIDIA Nemotron Nano 12B v2 VL？