NVIDIA › Llama 3.1 Nemotron 70B Instruct › Pricing

Llama 3.1 Nemotron 70B Instruct pricing

Cheapest host: DeepInfra · checked Oct 23, 2026
Benchmarks and alternatives →
$1.20 / $1.20per 1M tokens in / out

Price sheetper 1M tokens

Input$1.20DeepInfra
Output$1.20
Context131Ktokens

Where to buy1 provider · per 1M tokens

ProviderInputOutputContext
DeepInfra$1.20$1.20—

In NVIDIA's line-upper 1M in / out

NVIDIA Nemotron Nano 12B v2 VL$0.20 / $0.60−75%
Nemotron 3 Super 120B A12B$0.13 / $1.15−68%
Nemotron 3 Ultra$0.50 / $2.50−17%
Llama 3.1 Nemotron 70B Instruct$1.20 / $1.20this model
OpenCodeReasoning Nemotron 1.1 32B$2.72 / $4.802.7×
OpenReasoning Nemotron 32B$2.72 / $4.802.7×
Nemotron 4 340B Instruct$4.20 / $4.203.5×
<
All NVIDIA API prices →

Cheaper for the same workvs Llama 3.1 Nemotron 70B Instruct

Gemini 3 Flash Preview unstated-6%score wins 74%$0.50 / $3
MiMo v2.6 Pro unstatedOpen-55%score wins 73%$0.43 / $0.87
Gemini 3.5 Flash Lite unstated-29%score wins 72%$0.30 / $2.50
GLM 5.3 Flash unstatedOpen-80%score wins 71%$0.15 / $0.50
MiMo v2.5 Pro unstatedOpen-55%score wins 71%$0.43 / $0.87
All alternatives and what breaks when you switch →

Pricing questions

How much does Llama 3.1 Nemotron 70B Instruct cost?›

$1.20 per 1M input tokens and $1.20 per 1M output tokens.

Is Llama 3.1 Nemotron 70B Instruct free to use?›

There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.

What is a cheaper alternative to Llama 3.1 Nemotron 70B Instruct?›

Gemini 3 Flash Preview at unstated effort costs -6% per task with a score wins 74% on Arena Text · overall.