Nemotron 3 Ultra 550B A55B (Reasoning)
AI model by NVIDIA. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Nemotron 3 Ultra 550B A55B (Reasoning) is a budget-tier option from NVIDIA at $2.67/M output tokens. Despite the low price, it scores competitively on Coding Index (49.3) and Intelligence Index (38.3) — making it a candidate for high-volume production workloads where unit cost dominates.
Latency. On latency, Nemotron 3 Ultra 550B A55B (Reasoning) reports 159 tok/s output speed and 2720ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Nemotron 3 Ultra 550B A55B (Reasoning) costs $0.95 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 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Nemotron 3 Ultra 550B A55B (Reasoning)Current | $0.68 | $2.67 | 159 tok/s |
| DeepSeek V3.1 Terminus (Reasoning) | $1.64 | $2.75 | — |
| Llama 3 Instruct 70B | $0.65 | $2.75 | — |
| Qwen3 235B A22B (Non-reasoning) | $0.70 | $2.80 | 63 tok/s |
| Nova 2.0 Omni (medium) | $0.30 | $2.50 | — |
| Gemini 3.5 Flash-Lite | $0.30 | $2.50 | 391 tok/s |