Skip to main content
Back to Explore

Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)

NVIDIA·Released 2025-04-07
Open Source

Pricing

Input

$0.60

per 1M tokens

Output

$1.80

per 1M tokens

Blended

$0.90

per 1M tokens

Cheaper than 38% of models. Median price is $0.54/1M tokens.

Cost Calculator

Tokens per day1M
100K100M

Daily

$0.90

Monthly

$27.00

vs. Similar Models

GLM-4.5V (Reasoning)Q:0.0
$0.900%
Mistral Large 2 (Nov '24)Q:0.0
$3.00+233%
Mistral Small 3.2Q:0.0
$0.13-86%
Qwen3 30B A3B 2507 InstructQ:0.0
$0.21-76%

Performance

52

tokens/sec

Faster than 21% of models

0.71

seconds

Faster than 71% of models

38.98

seconds

Faster than 12% of models

Market Median

94 tok/s

45% slower

Median TTFT

1.11s

36% faster

Throughput/Dollar

58

tok/s per $/1M

Speed Comparison

Qwen: Qwen3.6 Plus
52 tok/s-0%
Qwen: Qwen3.5 397B A17B
52 tok/s-0%
MiniMax M2.7
52 tok/s-0%

Benchmarks

MMLU-Pro
82.5%
GPQA Diamond
72.8%
HLE
8.1%
LiveCodeBench
64.1%
SciCode
34.7%
TerminalBench Hard
2.3%
MATH-500
95.2%
AIME
74.7%
AIME 2025
63.7%
IFBench
38.2%
Long Context Recall
7.3%
Tau2
11.4%
Market AverageTop Score

Open Source

Quick Compare

Similar Models

Compare all 7 models