Meta AI

Llama 3.1 Nemotron Ultra 253B

Type
language model
Context
128K tokens
Max output
16K
Released
7 April 2025
API string
nvidia/llama-3.1-nemotron-ultra-253b-v1
Weights
open

Prices by provider

Provider Input, $ per 1M Output, $ per 1M In our data since
Nebius Token Factory $0.6 $1.8 31 Jul 2026

Only the base tier and only per-token prices are shown. Batch, discounted and cached rates, as well as prices per image or per second of video, do not go into this table: they cannot stand in the same column as a price per million tokens.

The date in the last column is the day this price first entered our collection. The price may well be older: before that day we simply were not recording it. It has not changed since — otherwise a new row with a new date would stand in its place.

Measurement results

Task set Result Run conditions Measured by
Arena Score, mathematics 1,359.51 1,322–1,397 — —
Arena Score in English 1,344.5 1,330–1,359 — —
Arena Score, overall 1,319.57 1,308–1,331 — —
Arena Score, multi-turn dialogue 1,317.09 1,287–1,347 — —
Arena Score, hard prompts 1,316.05 1,295–1,337 — —
Arena Score, creative writing 1,314.7 1,288–1,341 — —
Arena Score, programming 1,312.4 1,283–1,342 — —
Arena Score, instruction following 1,308.26 1,287–1,329 — —
Arena Score, long queries 1,298.83 1,269–1,329 — —
Arena Score in Russian 1,283.31 1,254–1,313 — —