Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is a text-based AI model by NVIDIA. It features 42 tok/s output speed, $0.60/1M input tokens pricing. It scores 15.0 on the intelligence index.
Strengths
- +Very affordable pricing ($0.60/1M tokens)
Weaknesses
- -Slower than average output (42 tok/s)
Benchmarks
Intelligence15.0Coding13.1Math63.7
MMLU-Pro
0.8
GPQA
0.7
LiveCodeBench
0.6
Intelligence
15.0
Coding
13.1
Math
63.7
Output Speed
42 tok/s
Latency (TTFT)
0.65s
Blended Price
$0.90/M
Pricing per 1M Tokens
| Input (Prompt) | $0.60 |
| Output (Completion) | $1.80 |
| Cache Read | Free |
| Cache Write | Free |
Specifications
| Context Length | N/A |
| Max Output Tokens | N/A |
| Input Modalities | Text |
| Output Modalities | Text |
| Tokenizer | N/A |
Compare Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) with:
Alternatives to Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
More from NVIDIA
Frequently Asked Questions
How much does Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) cost?
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) costs $0.60/1M input tokens and $1.80/1M output tokens.
Is Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) good for coding?
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) has a lower coding score of 13.1. For demanding coding tasks, consider a model with a higher coding benchmark.
How fast is Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)?
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) generates output at 42 tok/s. Time to first token is 0.65s.
Is there a free version of Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)?
No, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)?
Last updated: