NVIDIA: Nemotron 3 Ultra
Vendor: nvidia|
nemotron-3-ultraModalities
TextText
In / out price99% off99% cheaper than the provider's official price per 1M tokens.
$0.0038 / $0.0038 per 1M
Context
1M
Released
Jun 4, 2026
Overview
An open frontier model for reasoning and orchestration: 550B parameters, 55B active, a hybrid Transformer-Mamba MoE architecture with LatentMoE and native speculative decoding via MTP. Up to 1M context, tuned for long agentic workflows.
Context
1M
Max output
—
Released
Jun 4, 2026
Step-by-step reasoning
Yes
Open weights
Price per 1M tokens
Input and output cost the same, billed per actual usage — no subscriptions, no minimums.
Input
$0.0038/M
$0.600/M99% off99% cheaper than the provider's official price per 1M tokens.
Output
$0.0038/M
$2.40/M100% off100% cheaper than the provider's official price per 1M tokens.
Official list price: $0.600 / $2.40 per 1M
Performance
Gateway metrics for the last 24 hours.
Loading metrics…
FAQ
Are there any rate limits?
The default limit is request rate per key. Each key can be restricted by models, spend and IP in your dashboard.
How is billing calculated?
Pay as you go: one price per 1M tokens, input and output cost the same, charged proportionally to real usage.
Is streaming supported?
Yes, stream: true behaves exactly like in the OpenAI API — tokens arrive as they are generated.