NVIDIA: Nemotron Ultra
Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $2.20 → $2.50
- ↓ lowerInput $0.5 → $0.25
- ↓ lowerOutput $2.40 → $2.20
- ↓ lowerInput $0.6 → $0.5
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (7 omitted). Show free/$0 listings.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapestnemotron-3-ultra-550b-a55b | N/A | $0.25 | $2.50 | $0.25 | N/A |
| LiteLLMcheapestperplexity/perplexity/nemotron-3-ultra-550b-a55b | N/A | $0.25 | $2.50 | $0.25 | N/A |
| models.devnvidia/nemotron-3-ultra-550b-a55b | Kilo Gateway | $0.4 | $1.76 | $0.08 | 203K |
| models.devnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | CoreWeave | $0.5 | $2.15 | $0.1 | 262K |
| models.devdeepinfra/nemotron-3-ultra-550b-a55b | Eden AI | $0.5 | $2.20 | $0.1 | 262K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | NanoGPT | $0.5 | $2.50 | $0.15 | 512K |
| models.devnvidia/nemotron-3-ultra-550b-a55b:thinking | NanoGPT | $0.5 | $2.50 | $0.15 | 1M |
| LiteLLMnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | N/A | $0.5 | $2.15 | $0.1 | N/A |
| LiteLLMNVIDIA-Nemotron-3-Ultra-550B-A55B | N/A | $0.5 | $2.15 | $0.1 | N/A |
| LiteLLMdeepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | N/A | $0.5 | $2.20 | $0.1 | N/A |
| models.devnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | Baseten | $0.6 | $2.40 | $0.12 | 203K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | CommandCode | $0.6 | $2.40 | $0.12 | 1M |
| OpenRouternvidia/nemotron-3-ultra-550b-a55b | OpenRouter | $0.6 | $2.40 | $0.12 | 262K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | Vercel AI Gateway | $0.6 | $2.40 | $0.12 | 1M |
| models.devarkanecloud/nvidia/nemotron-3-ultra-550b-a55b | Eden AI | $0.6 | $3.50 | $0.2 | 512K |
| models.devnvidia/nemotron-3-ultra-550b-a55b | Together AI | $0.6 | $3.60 | $0.2 | 512K |
| LiteLLMnvidia/nemotron-3-ultra-550b-a55b | N/A | $0.6 | $3.60 | $0.2 | N/A |
| models.devnvidia-nemotron-3-ultra-550b-a55b | Venice AI | $0.625 | $3.13 | $0.1875 | 256K |
| models.devnemotron-3-ultra-550b-a55b | Kenari | $0.6857 | $4.29 | $0.0686 | 1M |
| models.devnvidia/Nemotron-3-Ultra-550b-a55b | Nebius | $1 | $3 | $0.12 | 1.0M |
| models.devnebius/nvidia/Nemotron-3-Ultra-550b-a55b | Eden AI | $1 | $3 | $1 | 1.0M |
| LiteLLMnvidia/Nemotron-3-Ultra-550b-a55b | N/A | $1 | $3 | $0.1 | N/A |
| LiteLLMNemotron-3-Ultra-550b-a55b | N/A | $1 | $3 | $0.1 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence22.9i
- AA coding49.3i
- AA agentic20.1i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.