Model Library
NVIDIAReleased April 7, 2025Llama Nemotron Ultra
NVIDIA · Released April 7, 2025
Intelligence score
9
At a glance
- Intelligence
- 9
- Speed
- 50.9tokens/sec
- Latency
- 2.43stime to first token
- Input price
- $0.60per 1M tokens
- Output price
- $1.80per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 253billions
Summary
Comparison summary
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight models of similar size (median: 25). Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) generates output at 50.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 61.7 t/s). Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) costs $0.60 per 1M input tokens (somewhat higher than average, median: $0.59) and $1.80 per 1M output tokens (better than average, median: $2.20), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Llama Nemotron Ultra |
|---|---|
| Provider | NVIDIA |
| Release date | April 7, 2025 |
| Intelligence score | 9 |
| Speed | 50.9 tokens/sec |
| Latency (TTFT) | 2.43s |
| Input price | $0.60 / 1M tokens |
| Output price | $1.80 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 253B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | NVIDIA Open Model License Agreement |
| API availability | — |
| Source | Model Intelligence legacy profile: llama-3-1-nemotron-ultra-253b-v1-reasoning |
Pricing
Token prices
Price per 1M tokens
Llama Nemotron Ultra, as listed in the catalog record
- Input$0.60
- Output$1.80
| Token type | Price per 1M |
|---|---|
| Input | $0.60 |
| Output | $1.80 |
Model Intelligence legacy profile: llama-3-1-nemotron-ultra-253b-v1-reasoning
FAQ · 19
Frequently asked questions
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) was released on April 7, 2025.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) was created by NVIDIA.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight models of similar size (median: 25).
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) generates output at 50.9 tokens per second (based on the median across providers serving the model), which is at the lower end compared to other open weight models of similar size (median: 61.7 t/s).
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) has a time to first token (TTFT) of 2.43s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight models of similar size (median: 2.01s).
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) costs $0.60 per 1M input tokens (somewhat higher than average, median: $0.59) and $1.80 per 1M output tokens (better than average, median: $2.20), based on the median across providers serving the model.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) costs $0.60 per 1M input tokens and $1.80 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.72 per 1M tokens. Pricing may vary by provider.
Yes, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) supports text input.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) supports text output.
No, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) does not support image input. It can only process text.
No, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is not multimodal. It only supports text input.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) has 253 billion parameters.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is released under the NVIDIA Open Model License Agreement license. This license allows commercial use.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is available via API through 1 provider.
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is available through 1 API provider.