Compute Screener
Updated 12:44 AM CDT

Nemotron 3 Ultra API price per 1M tokens: input, cached and output prices, price chart and history

# Lab/Bloomberg ticker USD / 1M tokens 1D 1W 1M Trend Chart (3M)
1
DeepSeek
$0.0278-0.7%-3.5%-5.8%▼ Strong 5.8-33.0% a month
2
AnthropicORNNTOKA
$0.538-6.0%-21.4%-35.9%▼ Strong 5.7-20.9% a month
3
StepFun
$0.223-0.8%-4.9%+216.6%▲ Strong 4.5+63.8% a month
4
Z.ai
$0.128-11.3%-23.9%-22.3%▼ Moderate 3.5-31.1% a month
5
Alibaba
$0.0694-0.3%-1.3%-24.4%▼ Moderate 3.1-58.6% a month
6
Meta
$0.01570.0%0.0%0.0%▼ Moderate 2.4-59.2% a month
7
Xiaomi
$0.0357+3.8%+14.8%+32.7%▲ Moderate 2.4+9.1% a month
8
MiniMax
$0.0370-8.9%-51.1%-63.1%▼ Moderate 2.3-16.1% a month
9
xAI
$0.7350.0%0.0%0.0%▲ Moderate 2.2+4.8% a month
10
Google
$0.261+6.8%+10.7%+85.1%▲ Moderate 2.1+13.0% a month
11
Moonshot AI
$0.592-6.1%-17.9%-23.2%▼ Weak 1.2-2.7% a month
12
OpenAIORNNTOKO
$0.173-2.6%-20.5%-49.9%▼ Weak 0.2-2.3% a month
13
NVIDIA
$0.2000.0%0.0%0.0%Weak 0.00.0% a month

Nemotron 3 UltraNVIDIA

$0.2000.0% (All)
USD / 1M tokens
Cache read $0.12 · Input $0.60 · Output $2.40 per 1M tokens, at 87% cache read, 12% input, 1% output
1D
1W
1M
3M
6M
YTD
1Y
0.0%
0.0%
0.0%
0.0%
—
—
—
#ModelAs ofShareUSD / 1M tokens
1Nemotron 3 UltraOct 31, 12:45 AM CDT100.0%$0.200

Break-even throughput by GPU

GPUUSD / GPU-hourTokens/s per GPU
B300$9.352,473
B200$7.822,069
H200$5.071,342
H100$3.71982
RTX PRO 6000$2.07548
A100$1.76464
L40S$1.41372
L40$0.96254
RTX 6000 Ada$0.92242
RTX A6000$0.58154
RTX 4090$0.55146

Gross margin calculator

Revenue—
GPU rental price$3.71
Gross profit—
Gross margin—

About Nemotron 3 Ultra

Nemotron 3 Ultra is a model from NVIDIA. Its posted API price is $0.60 per 1M input tokens, $0.12 per 1M cached input tokens and $2.40 per 1M output tokens, or $0.200 per 1M tokens at the mix of tokens agents send (87% cache read, 12% input, 1% output). Its price has not changed since Jun 29, 2026. It carries 100.0% of NVIDIA's API tokens and is one of the model in the NVIDIA token price index, $0.200 per 1M tokens today. Of the 34 models in the token index it is the 14th most expensive. At today's H100 rental price of $3.71 per GPU-hour, its break-even throughput is 982 tokens per second per GPU at its list price (3 input : 1 output). Prices are collected once a day, for each UTC day.

Models near this price

  • Step 5 Preview (StepFun): $0.234 per 1M tokens at the mix, $1.00 input and $2.70 output
  • GPT-6.1 Terra (OpenAI): $0.213 per 1M tokens at the mix, $1.00 input and $5.00 output
  • Gemini 3.8 Flash (Google): $0.193 per 1M tokens at the mix, $0.75 input and $3.75 output
  • Gemini 3.7 Flash (Google): $0.193 per 1M tokens at the mix, $0.75 input and $3.75 output
  • Mistral Large 4 (Mistral): $0.166 per 1M tokens at the mix, $0.70 input and $2.10 output
  • Qwen3.8 27B (Alibaba): $0.150 per 1M tokens at the mix, $0.425 input and $2.55 output

Cite as: Compute Screener, “Nemotron 3 Ultra API price”, computescreener.com/models/nemotron-3-ultra-550b-a55b. The figures are free to reuse under CC BY 4.0 with credit to Compute Screener.