Llama-3.1-Nemotron-Ultra-253B-v1 vs Nemotron 3 Ultra
Llama-3.1-Nemotron-Ultra-253B-v1 is cheaper on output tokens, while Nemotron 3 Ultra offers a larger context window. Choose Llama-3.1-Nemotron-Ultra-253B-v1 or Nemotron 3 Ultra based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Llama-3.1-Nemotron-Ultra-253B-v1 | Nemotron 3 Ultra |
|---|---|---|
| Provider | Nebius Token Factory | NVIDIA |
| Input / 1M tokens | $0.60 | $0.60 |
| Output / 1M tokens | $1.80 | $2.40 |
| Context window | 128K | 262K |
| Parameters | — | 550B |
| Open weights | Yes | Yes |
| Released | Jan 2025 | Jun 2026 |
| LMArena (Chatbot Arena) Elo score | 1320 | 1445 |
| LiveBench score | — | 50.7 |
| GPQA Diamond score | — | 85.3 |
| Epoch Capabilities Index score | — | 146 |
FAQ
Is Llama-3.1-Nemotron-Ultra-253B-v1 or Nemotron 3 Ultra cheaper?
Llama-3.1-Nemotron-Ultra-253B-v1 is cheaper on output tokens ($1.80 vs $2.40 per 1M).
Which has the larger context window, Llama-3.1-Nemotron-Ultra-253B-v1 or Nemotron 3 Ultra?
Nemotron 3 Ultra has the larger context window (262K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.