nvidia logo
nvidia

NVIDIA: Nemotron 3 Ultra

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). $0.50 per million input tokens, $2.20 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

模型概览

模型规格

上下文
262,144 tokens
最大输出
16,384 tokens
架构
text->text
分词器
Other
知识截止时间
暂未提供
内容审核
OPENROUTER

完整价格

同步自 OpenRouter。Token 价格均按每百万 Token 展示。

输入
$0.5
/M tokens
输出
$2.2
/M tokens
缓存读取
$0.1
/M tokens
API

模型配置

默认参数

temperature
1
top_p
0.95

推理能力

内容审核
默认参数
high
能力与模态
high, medium
API

快速调用

通过 OpenRouter 的 OpenAI 兼容 API 调用这个确切的模型 ID。

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nvidia/nemotron-3-ultra-550b-a55b","messages":[{"role":"user","content":"Hello!"}]}'
能力与模态

输入输出

输入
text
输出
text
推理能力

· high · medium

API

支持的 API 参数

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
可用提供方

3 个提供方

在 OpenRouter 查看实时 Provider

Provider 可用性、延迟、吞吐量和路由会持续变化,请前往来源页面查看实时运行数据。

OpenRouter

DeepInfra

fp4
上下文
262K
最大输出
16K
输入
$0.500
输出
$2.20
缓存读取
$0.100
缓存写入
暂未提供

BaseTen

fp4
上下文
203K
最大输出
183K
输入
$0.600
输出
$2.40
缓存读取
$0.120
缓存写入
暂未提供

Venice

fp8
上下文
256K
最大输出
33K
输入
$0.625
输出
$3.13
缓存读取
$0.188
缓存写入
暂未提供
nvidia

个模型

全部模型
nvidia logonvidia

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...

上下文
暂未提供
输入
audio
输出
transcription
输入: $3.33输出: 免费每百万 Token
查看模型详情
nvidia logonvidia

NVIDIA: Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

上下文
262K
输入
text
输出
text
输入: $0.080输出: $0.200每百万 Token
查看模型详情
nvidia logonvidia

NVIDIA: Nemotron 3.5 Lightning (free)

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

上下文
1M
输入
text
输出
text
输入: 免费输出: 免费每百万 Token
查看模型详情
nvidia logonvidia

NVIDIA: Nemotron 3 Embed 1B (free)

NVIDIA Nemotron 3 Embed 1B is an open text embedding model from NVIDIA, optimized for high-throughput, low-latency retrieval. It is suited for enterprise search, RAG, code retrieval, and agentic retrieval...

上下文
33K
输入
text
输出
embeddings
输入: 免费输出: 免费每百万 Token
查看模型详情