Nebius Token Factory

Llama-3.1-Nemotron-Ultra-253B-v1

Name: Llama-3.1-Nemotron-Ultra-253B-v1
Brand: Nebius Token Factory

Canonical ID: nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

More Nebius Token Factory models More llama-3-1-nemotron-ultra-253b-v1 family models

Llama-3.1-Nemotron-Ultra-253B-v1 is listed under Nebius Token Factory in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.

Reasoning: No Tool use: Yes

Overview

text

Provider: Nebius Token Factory
Family: llama-3-1-nemotron-ultra-253b-v1
Release date: 2025-01-15
Last updated: 2026-02-04
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.6/1M
Output: $1.8/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 4,096
Qualified ID: nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

Model Summary

Llama-3.1-Nemotron-Ultra-253B-v1 is a model listing in the Nebius Token Factory provider catalog. It is categorized under the llama-3-1-nemotron-ultra-253b-v1 family.

The model supports text modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0.6/1M input and $1.8/1M output.

Llama-3.1-Nemotron-Ultra-253B-v1

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Nebius Token Factory

Beam 1.0 501B A23B

BGE-ICL

bge-multilingual-gemma2

DeepSeek-R1-0528

DeepSeek R1 0528 Fast

DeepSeek-V3-0324

DeepSeek-V3-0324 (Fast)

DeepSeek-V3.2