NVIDIA logo

Llama 3.1 Nemotron 70B Instruct

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Llama 3.1 Nemotron 70B Instruct is NVIDIA's language model with a 131K context window and up to 16K output tokens, available from 2 providers, starting at $0.6 / 1M input and $0.6 / 1M output. A 70B instruction-tuned LLM fine-tuned by NVIDIA on Llama 3.1 to significantly improve helpfulness and response quality on user queries.
Specifications
Canonical IDnvidia-llama-3-1-nemotron-70b-instruct
TypeLanguage
StatusDeprecated
CreatorNVIDIANVIDIA
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters70B
HuggingFace Likes2,064
HuggingFace Downloads (30d)9,963
HuggingFace Downloads (all-time)1,815,075
Release Date · 2 years ago
Knowledge Cutoff · 3 years ago
Deprecation Date
Benchmarks
Intelligence Index
7.6
#355
Math Index
11.0
#222
MMLU-Pro
0.7
#215
GPQA
0.5
#356
HLE
0.0
#348
LiveCodeBench
0.2
#264
AIME
0.2
#85
IFBench
0.3
#339
Time to First Token
4.87s
#450
SciCode
0.2
#331
MATH-500
0.7
#118
AIME 2025
0.1
#222
LCR
0.1
#324
TerminalBench Hard
0.0
#269
TAU2
0.2
#286
Output TPS
280.3
#11

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
$0.6$0.6
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct
$0.9$0.9

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Llama 3.1 Nemotron 70B Instruct, ranked by cheapest on-demand price. The model needs about 168 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP40sAzure4× AMD Alveo U250 FPGA (64GB)256 GB$6.60/hrwestus2
g2-standard-96GCP8× nvidia-l4192 GB$7.98/hrus-east4
g7e.12xlargeAWS2× RTX PRO Server 6000192 GB$8.29/hrus-east-1
7 more instances can run Llama 3.1 Nemotron 70B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.120$0.200Deprecating
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
Llama 3.2 11B128K$0.160$0.160Available
Llama 3.1 405B Instruct131K$0.120$0.300Deprecated
Llama 3.1 8B Instruct200K$0.020$0.030Deprecated
Llama 3.1 70B Instruct131K$0.120$0.300Available
Llama 3.1 70B128K$0.360$0.360Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Deprecated
Llama 3.1 Nemotron 70B Instruct131K$0.600$0.600Current

Model IDs

accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct
deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct
fireworks_ai/accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct
llama-3-1-nemotron-instruct-70b
nvidia-llama-3-1-nemotron-70b-instruct
nvidia/llama-3.1-nemotron-70b-instruct
nvidia/Llama-3.1-Nemotron-70B-Instruct