Llama 3.1 Nemotron Ultra 253B

id: nvidia/llama-3.1-nemotron-ultra-253b

family: nemotron

context: 128,000

modalities: text → text

release: 2025-04-07

reasoning tools vision structured temp open weights

Offerings

Provider	Input	Output	Context	Max out
Nvidia nvidia/llama-3.1-nemotron-ultra-253b-v1	$0.00/M	$0.00/M	128,000	16,384
DevPass (LLM Gateway) llama-3.1-nemotron-ultra-253b	$0.60/M	$1.80/M	128,000	8,192

These provider models look related but are not exact matches.

Provider	Input	Output	Context	Max out
Cortecs llama-3.1-nemotron-ultra-253b-v1	$0.60/M	$1.79/M	128,000	128,000
Baseten nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B	$0.60/M	$2.40/M	202,800	202,800
LLM Gateway nebius/llama-3.1-nemotron-ultra-253b	$0.60/M	$1.80/M	128,000	128,000
Nebius Token Factory nvidia/Llama-3_1-Nemotron-Ultra-253B-v1	$0.60/M	$1.80/M	128,000	4,096