Nemotron Content Safety 3.5

by NVIDIA

Nemotron Content Safety 3.5 is a model from NVIDIA, released on June 1, 2026. It has a 131K-token context window and can generate up to 131K output tokens. API pricing is $0.2 per 1M input tokens and $0.2 per 1M output tokens.

Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-train models for safer behavior.

Key specs

ProviderNVIDIA
Release date2026-06-01
Licenseopen weights
Context window131K tokens
Max output131K tokens
Input price$0.2 / 1M tokens
Output price$0.2 / 1M tokens

Quick answers

What is the context window of Nemotron Content Safety 3.5?

Nemotron Content Safety 3.5 has a context window of 131K tokens, with a maximum output of 131K tokens per response.

How much does Nemotron Content Safety 3.5 cost?

Nemotron Content Safety 3.5 costs $0.2 per 1M input tokens and $0.2 per 1M output tokens through the API.

Is Nemotron Content Safety 3.5 open source?

Yes. Nemotron Content Safety 3.5 is an open model released under the open weights license.

When was Nemotron Content Safety 3.5 released?

NVIDIA released Nemotron Content Safety 3.5 on June 1, 2026.

Compare on the AI leaderboard · All AI models

More models from NVIDIA