NVIDIA: Nemotron 3 Ultra
NVIDIA
nvidia/nemotron-3-ultra-550b-a55bAbout this model
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Make a request
OpenAI-compatible: set the base URL and your Promptix API key, keep your existing SDK.
curl https://promptix.tn/api/v1/chat/completions \ -H "Authorization: Bearer $PROMPTIX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nvidia/nemotron-3-ultra-550b-a55b", "messages": [ {"role": "user", "content": "Hello! What can you do?"} ] }'Pricing
In TND per 1M tokens. VAT and the platform fee are added at top-up.
Input tokens
2.323 TNDper 1M tokens
Output tokens
9.290 TNDper 1M tokens
1,000 requests with 1K input and 500 output tokens cost about 6.968 TND.
Specifications
- Provider
- NVIDIA
- Context window
- 262,144 tokens
- Input modality
- Text
- Added
- Jun 4, 2026
- Supported parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effort