Llama 3.1 Nemotron Ultra 253B

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

Maker: NVIDIA, United States
Released: 2025-04-07
Family: nemotron
Weights: open
Tasks: text.chat, text.reasoning, code

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
NVIDIA API Catalog	`nvidia/llama-3.1-nemotron-ultra-253b-v1`	deprecated	Input: unknown Output: unknown	none	Context: 128,000 tokens Max output: 16,384 tokens	`input.text` claimed `output.text` claimed `tools` claimed `reasoning` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`lmarena:text_style_control`	0.540	1347.5732	2026-10-28	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

nvidia/llama-3.1-nemotron-ultra-253b-v1

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/nvidia/llama-3.1-nemotron-ultra-253b' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=nvidia' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.13 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).