Model Library/Nemotron 3 Nano 30B A3B
N

Nemotron 3 Nano 30B A3B

nvidia/nemotron-3-nano-30b-a3b
Nemotron-3-Nano-30B-A3B is NVIDIA's compute-efficient, open-weight reasoning model built for agentic AI. Its Mixture-of-Experts design (30B total / 3.5B active) with a hybrid Mamba-2 + Transformer architecture delivers strong reasoning and tool use at a fraction of the compute required by comparable dense models. It supports a 256K context window, toggleable chain-of-thought reasoning, function calling, and structured (JSON) outputs — making it well-suited for long-context agents, coding, and math. Released under the NVIDIA Nemotron Open Model License and ready for commercial use.

功能

Serverless API

文档

nvidia/nemotron-3-nano-30b-a3b is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

可用的 Serverless

立即运行查询,仅按用量付费

输入$0.05 / M Tokens
输出$0.2 / M Tokens

使用以下代码示例与我们的 API 集成:

1from openai import OpenAI
2
3client = OpenAI(
4    api_key="<Your API Key>",
5    base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9    model="nvidia/nemotron-3-nano-30b-a3b",
10    messages=[
11        {"role": "system", "content": "You are a helpful assistant."},
12        {"role": "user", "content": "Hello, how are you?"}
13    ],
14    max_tokens=32768,
15    temperature=0.7
16)
17
18print(response.choices[0].message.content)

信息

提供商
Nvidia
量化
fp4

支持的功能

上下文长度
262144
最大输出
32768
Serverless
支持
Function Calling
支持
Structured Output
支持
Reasoning
支持
输入能力
text
输出能力
text

构建生产级 AI 所需的一切。

200+ 个模型、按需 GPUs 和安全的智能体运行时——统一在一个 API 下。免费开始,随业务增长灵活扩展。