Nemotron 3 Ultra pricing
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... Live index: 3 priced offers. Best input $0.600 per million tokens from Openrouter. Best output $2.40 per million tokens from Openrouter.
Pricing across providers
Every row is a seller of Nemotron 3 Ultra with token pricing we track. The cheapest input in this snapshot is from Openrouter. The bar chart shows the same input and output dollars per million for a quick scan.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
N Nebius | $1.00 | $3.00 | — | — |
O Openrouter | $0.600 | $2.40 | — | — |
TA Together AI | $0.600 | $3.60 | $0.200 | — |
Input vs output · per provider
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Nemotron 3 Ultra cost scales with traffic.
Provider
0.100000¢ / req
0.150000¢ / req
Model specifications
Context length, caps, and capability flags for Nemotron 3 Ultra. Values follow the main provider (Nvidia) record in our index.
- Context window
- 1,000,000 tokens
- Max output
- 16,384 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Jun 2026
- Primary provider
- Nvidia
- Model family
- N/A
Compare Nemotron 3 Ultra
Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Nemotron 3 Ultra.
Locked
Compare with
Pick a model on both sides.
Popular Nemotron 3 Ultra comparisons
- Nemotron 3 Ultra vs GPT-4o
Compare pricing side by side
- Nemotron 3 Ultra vs Claude Sonnet 4.6
Compare pricing side by side
- Nemotron 3 Ultra vs Gemini 2.0 Flash
Compare pricing side by side
- Nemotron 3 Ultra vs Llama 3.1 70B
Compare pricing side by side
- Nemotron 3 Ultra vs Mistral 7B
Compare pricing side by side
- Nemotron 3 Ultra vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Related models
Models close to Nemotron 3 Ultra by family, provider, and context window — each with live pricing in our catalog.