Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
AI model by NVIDIA. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is a budget-tier option from NVIDIA at $1.80/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) reports 48 tok/s output speed and 2340ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) costs $0.78 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)Current | $0.60 | $1.80 | 48 tok/s |
| GLM-4.5V (Non-reasoning) | $0.60 | $1.80 | 92 tok/s |
| GLM-4.5V (Reasoning) | $0.60 | $1.80 | 83 tok/s |
| DeepSeek V3.1 (Reasoning) | $0.59 | $1.69 | — |
| DeepSeek V3.1 (Non-reasoning) | $0.56 | $1.68 | — |
| DeepSeek V3.1 (Non-reasoning) | $0.56 | $1.68 | — |