Nemotron Nano 30B

nvidianvidia/nemotron-nano-30b

NVIDIA's efficient hybrid model (30B total, 3.5B active MoE). Mamba-2 + Attention layers with 1M context for edge deployment.

上下文长度

最大输出

262K

输入价格

$0.072每百万 Tokens

输出价格

$0.288每百万 Tokens

模态能力

文本→文本

价格明细

类型	费率
输入	$0.072 每百万 Tokens
输出	$0.288 每百万 Tokens

支持参数

temperaturemax_tokenstop_ptoolstool_choiceresponse_formatstop

API 使用示例

cURL

curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "nvidia/nemotron-nano-30b",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'