Nvidia: Nemotron Nano 12B v2 VL

Nemotron multimodal model for visual reasoning and agentic AI workflows

Model lab: Nvidia
Model family: nemotron

Modalitiestext, image, video → text

Context window128,000

Maximum output128,000

Input · Context ≤ 128000 tokens · Maximum output 16384 tokensUSD 0.16 / 1M tokens

Output · Context ≤ 128000 tokens · Maximum output 16384 tokensUSD 0.48 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to nvidia/nemotron-nano-12b-v2-vl.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "nvidia/nemotron-nano-12b-v2-vl"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Nemotron Nano 12B v2 VL API Pricing

Type	Price information
Input · Context ≤ 128000 tokens · Maximum output 16384 tokens	USD 0.16 / 1M tokens
Output · Context ≤ 128000 tokens · Maximum output 16384 tokens	USD 0.48 / 1M tokens
Cached input · Context ≤ 128000 tokens · Maximum output 16384 tokens	USD 0.032 / 1M tokens

Benchmarks

Non-reasoning

Intelligence Index · v4.35.8

Coding Index—

Agentic Index—

Reasoning

Intelligence Index · v4.37.5

Coding Index—

Agentic Index—

Performance

Output speed200.96 tokens/s

Time to first token1.11 s

Time to first answer token—

End-to-end response time—

Measurement variant	Output speed	Time to first token	Time to first answer token	End-to-end response time
Non-reasoning	200.96 tokens/s	1.11 s	—	—

Performance trends

Throughput200.96 tok/sCurrent

Time to first token1.11 sCurrent

End-to-end latency7.1 sCurrent

Throughput

Current200.96 tok/s

Window average203.7 tok/s

Time to first token

Current1.11 s

Window average1.2 s

End-to-end latency

Current7.1 s

Window average7.5 s

Tail latency (P99)

Current14.7 s

Window average16.4 s

Prompt cache hit rate

Current31.1%

Window average23.3%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Nemotron Nano 12B v2 VL Compare models

Model	Input price	Output price	Context window	Capabilities
Nemotron Nano 12B v2 VLThis page	USD 0.16 / 1M tokens · Context ≤ 128000 tokens · Maximum output 16384 tokens	USD 0.48 / 1M tokens · Context ≤ 128000 tokens · Maximum output 16384 tokens	128,000	Text output · Reasoning · Tool calling
Nemotron 3.5 Super VL 120B A12B	USD 0.24 / 1M tokens	USD 0.72 / 1M tokens	1,048,576	Text output · Reasoning · Tool calling
Nemotron 3.5 Lightning 30B A3B	USD 0.04 / 1M tokens	USD 0.16 / 1M tokens	262,144	Text output · Reasoning · Tool calling
Nemotron 3 Ultra 550B A55B	USD 0.4 / 1M tokens	USD 1.76 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
Nemotron 3.5 Content Safety	USD 0.04 / 1M tokens	USD 0.12 / 1M tokens	128,000	Text output · Reasoning

Model specifications

Input: text, image, video
Output: text
Context window: 128,000
Maximum output: 128,000
Release date: 2025-10-28
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is Nemotron Nano 12B v2 VL for?

Nemotron multimodal model for visual reasoning and agentic AI workflows

What inputs and outputs does Nemotron Nano 12B v2 VL support?

Recorded inputs: text, images, video; outputs: text.

How is Nemotron Nano 12B v2 VL priced?

The pricing table shows the current recorded Moduck price. For example: Input · Context ≤ 128000 tokens · Maximum output 16384 tokens USD 0.16 / 1M tokens; Output · Context ≤ 128000 tokens · Maximum output 16384 tokens USD 0.48 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Nemotron Nano 12B v2 VL?

Current model records list Context window 128,000 tokens; Maximum output 128,000 tokens.

What model parameter does the Quickstart use?

The example uses nvidia/nemotron-nano-12b-v2-vl. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.