Context
128K
Max output
128K
Serving providers
1
Cheapest input
$0.60 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%reasoning: true
EvalComputeProxy498.8reasoning: true
GPQA Diamond73%reasoning: true
Humanity's Last Exam8%reasoning: true
IFBench38%reasoning: true
LiveCodeBench64%reasoning: true
Long-Context Reasoning7%reasoning: true
MMLU-Pro82%reasoning: true
Omniscience-45.5reasoning: true
SciCode35%reasoning: true
TerminalBench Hard2%reasoning: true
τ²-bench11%reasoning: true

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
NebiusCheapest$0.60$1.801
ComponentUnitStandardBatchCached
Text input/1M tok$0.6000
Text output/1M tok$1.80

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00$1.50$2.00Jul 30Mar 3Jun 22$1.80$0.600

Cost calculator

estimate your monthly spend on this model
$264
estimated / month

Model IDs

copy the exact identifier for your platform
nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1

Frequently asked questions

Llama 3.1 Nemotron Ultra 253B pricing, context and availability

How much does Llama 3.1 Nemotron Ultra 253B cost?

Llama 3.1 Nemotron Ultra 253B costs $0.60 per 1M input tokens and $1.80 per 1M output tokens at its cheapest provider via Nebius.

What is the context window of Llama 3.1 Nemotron Ultra 253B?

Llama 3.1 Nemotron Ultra 253B accepts up to 128K tokens of context and can return up to 128K output tokens.

What can Llama 3.1 Nemotron Ultra 253B do?

Llama 3.1 Nemotron Ultra 253B supports tool use.

Other NVIDIA models

compare pricing across the NVIDIA lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI