How much does Nemotron 3.5 Content Safety cost via API?

It's free — $0 per 1M input tokens and $0 per 1M output tokens, both from the provider and on OpenKey (provider price $0 x 1.03 fee = $0). There's no cost math to do because the base price is zero.

What is Nemotron 3.5 Content Safety's context window?

It supports 128,000 tokens of context, enough to hold a long chat thread or a lengthy document for a single moderation pass. That puts it larger than 12% of models in the OpenKey catalog, though many chat-focused models exceed it.

Is Nemotron 3.5 Content Safety free to use?

Yes. Both the provider price and the OpenKey price are $0 per 1M tokens for prompt and completion, making it one of the free models on the platform alongside other free-tier Nemotron variants like Nemotron 3 Super (free) and Nemotron 3 Ultra (free).

Does Nemotron 3.5 Content Safety support vision and reasoning?

Yes to both. It accepts text and image input (text+image->text modality), and it supports optional reasoning that's enabled by default but not mandatory per request — useful if you want the model to explain a moderation decision, not just output a flag.

How does Nemotron 3.5 Content Safety compare to other Nemotron models?

It's a specialized 4B-parameter moderation model, not a general chat model like its siblings. Nemotron 3 Nano 30B A3B ($0.05/$0.2 per 1M) and Nemotron 3 Super ($0.085/$0.4 per 1M) are built for general tasks, while this one exists to classify content safety on inputs and outputs from other LLMs and VLMs.

Nemotron 3.5 Content Safety (free)

nvidianemotron-3.5-content-safety:free

Free

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...

Try in playground Hugging Face ↗

Modalities: text + image → text
In / out per 1M: Free / Free
Context: 128K tokens
Added: Jun 4, 2026

Max output: 8K tokens
Tokenizer: Other
Reasoning: optional

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokens	Provider	+ 3% fee	You pay
Input	Free	—	Free
Output	Free	—	Free

Providers

One company serves Nemotron 3.5 Content Safety (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.

Provider	Context	Input /M	Output /M
Nvidia	128K	Free	Free

Provider list from the OpenRouter catalog, Jul 28, 2026. All providers

Supported parameters

include_reasoning
max_tokens
reasoning
seed
temperature
top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model nvidia/nemotron-3.5-content-safety:free.

curl Python TypeScript

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer ***" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3.5-content-safety:free",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="nvidia/nemotron-3.5-content-safety:free",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "nvidia/nemotron-3.5-content-safety:free",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

About Nemotron 3.5 Content Safety (free)

Nemotron 3.5 Content Safety is a 4B-parameter guardrail model NVIDIA fine-tuned from Google's Gemma-3-4B. Instead of generating open-ended answers, it classifies inputs to and outputs from other LLMs and VLMs, flagging unsafe content before it reaches a user or gets sent to a model. It takes both text and image input and returns a text verdict, with a 128,000-token context window and up to 8,192 completion tokens per call — enough room to screen long conversations or documents in one pass rather than chunking them.

It's free on OpenKey (provider price and OpenKey price both $0 per 1M tokens, prompt and completion), unlike most of its Nemotron siblings — Nemotron 3 Super runs $0.085/$0.4 per 1M and Nemotron 3 Ultra runs $0.5/$2.2 per 1M (input/output). At 128,000 tokens, its context window is larger than 12% of catalog models, which is modest for a general chat model but plenty for a moderation classifier. It also accepts image input alongside text, which most guardrail models don't.

Questions

How much does Nemotron 3.5 Content Safety cost via API?: It's free — $0 per 1M input tokens and $0 per 1M output tokens, both from the provider and on OpenKey (provider price $0 x 1.03 fee = $0). There's no cost math to do because the base price is zero.
What is Nemotron 3.5 Content Safety's context window?: It supports 128,000 tokens of context, enough to hold a long chat thread or a lengthy document for a single moderation pass. That puts it larger than 12% of models in the OpenKey catalog, though many chat-focused models exceed it.
Is Nemotron 3.5 Content Safety free to use?: Yes. Both the provider price and the OpenKey price are $0 per 1M tokens for prompt and completion, making it one of the free models on the platform alongside other free-tier Nemotron variants like Nemotron 3 Super (free) and Nemotron 3 Ultra (free).
Does Nemotron 3.5 Content Safety support vision and reasoning?: Yes to both. It accepts text and image input (text+image->text modality), and it supports optional reasoning that's enabled by default but not mandatory per request — useful if you want the model to explain a moderation decision, not just output a flag.
How does Nemotron 3.5 Content Safety compare to other Nemotron models?: It's a specialized 4B-parameter moderation model, not a general chat model like its siblings. Nemotron 3 Nano 30B A3B ($0.05/$0.2 per 1M) and Nemotron 3 Super ($0.085/$0.4 per 1M) are built for general tasks, while this one exists to classify content safety on inputs and outputs from other LLMs and VLMs.

More from NVIDIA

All NVIDIA models →

NVIDIA

Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

ctx 1M in $0.515 out $2.27

NVIDIAFree

Nemotron 3 Ultra (free)

ctx 1M in Free out Free

NVIDIAFree

Nemotron 3 Nano Omni (free)

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...

ctx 256K in Free out Free

NVIDIA

Nemotron 3 Super

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...

ctx 1M in $0.088 out $0.412