llama-3.1-nemotron-safety-guard-8b-v3 是 NVIDIA 推出的 开源权重模型，上下文窗口 128,000 tokens，单次最大输出 4,096 tokens。
原厂描述：Safety model for policy screening, moderation, and risk-aware routing workflows
nvidia/llama-3.1-nemotron-safety-guard-8b-v3数据来源：models.dev。
# Python OpenAI SDK 调用示例 import openai client = openai.OpenAI( api_key="your-api-key", base_url="https://api.eake.cn/v1" ) response = client.chat.completions.create( model="md-nvidia-llama-3-1-nemotron-safety-guard-8b-v3", messages=[ {"role": "user", "content": "你好！"} ], temperature=0.7, max_tokens=2048 ) print(response.choices[0].message.content)
https://api.eake.cn/v1
完全兼容 OpenAI API 格式，可直接使用官方 SDK 调用