Nemotron-4-340B
Large
Nemotron-4 340B, NVIDIA's 2024 dense flagship. Designed primarily as a synthetic data generator for downstream training.
Nemotron-4-340B is a frontier AI model from Nvidia. It costs $4.200 per million input tokens and $4.200 per million output tokens (blended $4.200/M), with a 4,000-token context window.
INPUT
$4.200/M
per million input tokens
OUTPUT
$4.200/M
per million output tokens
CONTEXT
4,000
tokens
What it is good at
- 340B dense parameters
- Synthetic data generation focus
- Open weights
Typical use cases
- Synthetic data pipelines
- Distillation source
- Quality-ceiling research
Benchmarks
vs. best public score
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.
More from Nvidia
See all 6 →Llama-3.1-Nemotron-70B
RLHF-Aligned · 128,000 ctx
in $0.350/Mout $0.400/M
Llama-3.1-Nemotron-Ultra-253B
Ultra · 128,000 ctx
in $1.600/Mout $1.600/M
Mistral-NeMo-12B (NIM)
Efficient · 128,000 ctx
in $0.150/Mout $0.150/M
Phi-3-Mini-4K (NIM)
Nano · 4,000 ctx
in $0.040/Mout $0.040/M
Mistral-Large-2 (NIM)
Enterprise · 128,000 ctx
in $2.000/Mout $6.000/M
Frequently asked questions
How much does Nemotron-4-340B cost?
Nemotron-4-340B costs $4.200 per million input tokens and $4.200 per million output tokens, for a blended reference rate of $4.200 per million tokens.
What is Nemotron-4-340B's context window?
Nemotron-4-340B supports up to 4,000 tokens of context in a single request.
What is Nemotron-4-340B best for?
Nemotron-4-340B is well suited to 340B dense parameters, Synthetic data generation focus and Open weights.
Who makes Nemotron-4-340B?
Nemotron-4-340B is developed and served by Nvidia. It was released in Jun 2024.