Context
131K
Max output
131K
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
Speed & latency
Output speed
285 t/s
tokens / second
Time to first token
8.40s
latency
Headline indices
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy133.1default
GPQA Diamond46%default
Humanity's Last Exam5%default
IFBench31%default
LiveCodeBench17%default
Long-Context Reasoning7%default
MMLU-Pro69%default
Omniscience-41.0default
SciCode23%default
TerminalBench Hard5%default
τ²-bench23%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfraCheapest$0.60$0.601
ComponentUnitStandardBatchCached
Text input/1M tok$0.6000
Text output/1M tok$0.6000

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.100$0.200$0.300Jul 30Sep 26Oct 4Jun 22$0.300$0.120

Cost calculator

estimate your monthly spend on this model
$168
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct

Frequently asked questions

Llama 3.1 Nemotron 70B Instruct pricing, context and availability

How much does Llama 3.1 Nemotron 70B Instruct cost?

Llama 3.1 Nemotron 70B Instruct costs $0.60 per 1M input tokens and $0.60 per 1M output tokens at its cheapest provider via DeepInfra.

What is the context window of Llama 3.1 Nemotron 70B Instruct?

Llama 3.1 Nemotron 70B Instruct accepts up to 131K tokens of context and can return up to 131K output tokens.

What can Llama 3.1 Nemotron 70B Instruct do?

Llama 3.1 Nemotron 70B Instruct 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