Nvidia Nemotron 3 Ultra 550B
nano-gpt / nvidia/nemotron-3-ultra-550b-a55b
Input price
$0.5
per 1M tokens
Output price
$2.5
per 1M tokens
Context
512K
tokens
Capabilities
✓ Reasoning✓ Tool calls— Image input✓ Open weights
| cache read | $0.15 |
| Context | 512,288 tokens |
| max output | 65,536 tokens |
| Released | 2026-06-04 |
| Data updated | 2026-06-04 |
⚠ The two sources disagree on price
models.dev says $0.5, LiteLLM says $0.6. We do not average or guess — both raw values are in models.json, see for yourself.
Prices are official/data-source rates (per 1M tokens), not what relays actually charge — relay prices vary with discounts and group multipliers. See methodology.