NVIDIAactiveOpen Source

Nemotron 70B Instruct

llama-3.1-nemotron-70b

NVIDIA-optimized Llama 3.1 70B with reward model alignment.

Context Window

131.1K

tokens

Max Output

4.1K

tokens

Input Price

—

per 1M tokens

Output Price

—

per 1M tokens

Details

Familynemotron

Parameters70B

Training Cutoff2024-06-01

ReleasedOctober 15, 2024

FunctionsStreamingJSON ModeCodeTool Use

HumanEvalFunction-level Python code generation

72.8%

MMLU-ProHarder successor to MMLU

60.2%

MATH-500Competition-style math

58.5%

curl pikaainews.com/api/models/nvidia-nemotron-70b-instruct

npx pika-models info nvidia-nemotron-70b-instruct

Third-Party Providers & Aggregators

DeepInfra

Lowest per-token rates for open-source models.

Nemotron Super 49B

llama-3.3-nemotron-super-49b

Nemotron-70B

nemotron-70b