NVIDIA
Nemotron 3 Ultra 550B A55B
Nemotron 3 Ultra 550B A55B by NVIDIA — compare inference API pricing across providers.
Input from
$0.500 / 1M tokens
across 2 providers
API Pricing
Cheapest on OpenRouter — 9% below avg| Provider | Input / 1M | Output / 1M | Cached / 1M |
|---|---|---|---|
| $0.500 | $2.20 | $0.100 | |
| $0.600 | $3.60 | - |
Prices updated daily. Last check: Jun 23, 2026
Performance & Benchmarks
Source: Artificial Analysis →Intelligence
37.8 / 100
Coding
49.3 / 100
Output Speed
144 t/s
Latency (TTFT)
927ms
Reasoning & Knowledge
- GPQA Diamond86.7%
- Humanity's Last Exam26.6%
Coding
- SciCode39.9%
Agentic & Tool Use
- Terminal-Bench Hard36.4%
- Terminal-Bench v2.153.9%
- τ²-bench83.3%
- τ-bench Banking13.8%
Instruction & Long Context
- IFBench81.4%
- Long-Context Reasoning67.0%
Benchmarks measured Jun 2026. Scores are independent evaluations, not vendor-reported.
Model Details
General
- Creator
- NVIDIA
- Modalities
- Text
Capabilities
- Tool Calling
- No
- Open Source
- No