Llama 3.1 Nemotron Safety Guard 8B v3
多语言内容安全模型，审核人类与 LLM 交互的内容，并将用户提示词和 LLM 回复分类为安全或不安全。
规格
- 上下文
- —
- 最大输出
- —
- 输入价
- —
- 输出价
- —
- 发布日期
- 2025-10-28
上下文
- 官方未公布
价格
- 官方未公布
输入输出
- 输入
- 文本
- 输出
- 文本
API
- 接口类型
思考
- 官方未公布
源信息
- 状态
- 可用
- 发布日期
- 2025-10-28
- 知识截止
- —
能力
- 官方未公布
调用方式
1 个 Provider
nvidiamodel = nvidia/llama-3.1-nemotron-safety-guard-8b-v3
JSON
标准格式
{
"id": "llama-3.1-nemotron-safety-guard-8b-v3",
"object": "model",
"created": 1761609600,
"owned_by": "nvidia",
"name": "Llama 3.1 Nemotron Safety Guard 8B v3",
"api": {
"types": [
"moderation"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"reasoning": {
"supported": null,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "active",
"release_date": "2025-10-28",
"knowledge_cutoff": null,
"description": "Multilingual content safety model that moderates human-LLM interaction content and classifies user prompts and LLM responses as safe or unsafe.",
"docs": "https://docs.api.nvidia.com/nim/reference/nvidia-llama-3_1-nemotron-safety-guard-8b-v3",
"verified_at": "2026-10-11"
}
}官方来源
1