Nvidia
Nemotron 3 Ultra 550B A55B Pricing
API pricing for Nemotron 3 Ultra 550B A55B by Nvidia. Input tokens cost $0.5/1M, output tokens cost $2.5/1M with 1M context window.
Last updated:
ReasoningTools
Input Cost
$0.5
per 1M tokens
Output Cost
$2.5
per 1M tokens
Context Window
1M
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Provider Nvidia
Model ID nvidia/nemotron-3-ultra-550b-a55b
Context Window 1M tokens
Max Output 65536 tokens
Cache Read Cost $0.15/1M
Release Date 2026-06-04
Sources
Compare Alternatives
| Model | Input | Output | Context |
|---|---|---|---|
| Nemotron 3 Ultra 550B A55B (this model) | $0.5 | $2.5 | 1M |
| MiniMax-M2.5-highspeed MiniMax (minimax.io) | $0.6 | $2.4 | 205K |
| MiniMax-M2.7-highspeed MiniMax (minimax.io) | $0.6 | $2.4 | 205K |
| MiniMax-M2.5-highspeed MiniMax (minimaxi.com) | $0.6 | $2.4 | 205K |
| MiniMax-M2.7-highspeed MiniMax (minimaxi.com) | $0.6 | $2.4 | 205K |
| Grok Build 0.1 xAI | $1 | $2 | 256K |
Available from Resellers
Nemotron 3 Ultra 550B A55B is also available through these resellers and gateways:
| Reseller | Model | Input | Output |
|---|---|---|---|
| Baseten | Nemotron Ultra | $0.6 | $2.4 |
| Kilo Gateway | Nemotron 3 Ultra 550B A55B | $0.5 | $2.2 |
| LLM Gateway | Llama 3.1 Nemotron Ultra 253B | $0.6 | $1.8 |
| LLM Gateway | Nemotron 3 Ultra 550B A55B | $0.5 | $2.5 |
| Nebius Token Factory | Llama-3.1-Nemotron-Ultra-253B-v1 | $0.6 | $1.8 |
| OpenRouter | Nemotron 3 Ultra 550B A55B | $0.6 | $3.6 |
| Pioneer | Nemotron 3 Ultra 550B A55B | $0.5 | $2.5 |
| routing.run | Nemotron 3 Ultra 550B A55B | $0.1 | $0.1 |
| Together AI | Nemotron 3 Ultra 550B A55B | $0.6 | $3.6 |
| Venice AI | NVIDIA Nemotron 3 Ultra | $0.625 | $3.125 |