Claude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/MClaude Fable 5$22.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MGemini 1.5 Pro$2.375/MGemini 1.0 Ultra$12.000/MGemini 1.0 Pro$0.800/M
BETA
Subscribe
← Back to Index·All Nvidia models
Nvidia
NvidiaFrontier

Llama-3.1-Nemotron-Ultra-253B

Ultra

Nemotron Ultra — NVIDIA's flagship Nemotron tuned over Llama 3.1. 253B parameter dense model targeting frontier-class quality.

Llama-3.1-Nemotron-Ultra-253B is a frontier AI model from Nvidia. It costs $1.600 per million input tokens and $1.600 per million output tokens (blended $1.600/M), with a 128K-token context window.

Modalities textOfficial model page ↗API docs ↗Compare with another model →Estimate monthly cost →
INPUT
$1.600/M
per million input tokens
OUTPUT
$1.600/M
per million output tokens
BLENDED 70/30
$1.600/M
default reference rate · how it's calculated →
CONTEXT
128K
128,000 tokens
What it's good at
  • Largest Nemotron
  • Open weights
  • NVIDIA NIM hosting
Typical use cases
  • Frontier-class self-hosted inference
  • Synthetic data generation
Benchmarks
vs. best public score
MMLU88%
Multitask academic knowledge across 57 subjects.
GPQA Diamond60%
Graduate-level science questions, "Google-proof".
MATH80%
High-school competition math problems.
HumanEval86%
Python function synthesis from docstrings.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources — treat as directional rather than authoritative.
More from Nvidia
See all 6 →
Llama-3.1-Nemotron-70B
RLHF-Aligned · 128K ctx
in $0.350/Mout $0.400/M
Nemotron-4-340B
Large · 4K ctx
in $4.200/Mout $4.200/M
Mistral-NeMo-12B (NIM)
Efficient · 128K ctx
in $0.150/Mout $0.150/M
Phi-3-Mini-4K (NIM)
Nano · 4K ctx
in $0.040/Mout $0.040/M
Mistral-Large-2 (NIM)
Enterprise · 128K ctx
in $2.000/Mout $6.000/M
Frequently asked questions

How much does Llama-3.1-Nemotron-Ultra-253B cost?

Llama-3.1-Nemotron-Ultra-253B costs $1.600 per million input tokens and $1.600 per million output tokens, for a blended reference rate of $1.600 per million tokens.

What is Llama-3.1-Nemotron-Ultra-253B's context window?

Llama-3.1-Nemotron-Ultra-253B supports up to 128K tokens of context (128,000 tokens).

What is Llama-3.1-Nemotron-Ultra-253B best for?

Llama-3.1-Nemotron-Ultra-253B is well suited to Largest Nemotron, Open weights and NVIDIA NIM hosting.

Who makes Llama-3.1-Nemotron-Ultra-253B?

Llama-3.1-Nemotron-Ultra-253B is developed and served by Nvidia.