Nemotron 3.5 Content Safety · deepinfra

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.

Базовая модельВсе модели этой базовойВсе модели провайдерак провайдеру

Все модели NVIDIA у всех провайдеров

Вход, $/1M $0.20

Выход, $/1M $0.20

Контекст 131 072

Принимает —

Последняя проверка 04.11.2026 12:00:14 UTC

Источник —