Skip to content
Model Pulse

Model

Llama 3.1 Nemotron Ultra 253B

Flagship Nemotron model for high-throughput reasoning and complex agents

1 providers · 1 listingsreleased open weights
Free
cheapest listed tier
128K
context window
16K
max output

Compare providers (sorted by listed input price)

1 listings
Cache read /MCache write /MCapabilitiesStatus
Nvidia
nvidia/llama-3.1-nemotron-ultra-253b-v1
————128Kreasoningtoolsno structuredno visionApr 7, 2025
1–1 of 1 listings

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0▼ 100.0%
Best output /M
$0▼ 100.0%
Provider coverage
1
3 at the start · 24 snapshots
Best published input and output price historyDaily lowest published price per one million tokens. Accent is input price and violet is output price. The vertical scale starts at zero.$0$0.972$1.94Aug 21, 2026Sep 1, 2026Sep 14, 2026
Best input priceBest output priceAug 21, 2026 → Sep 14, 2026

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.