NVIDIA: Nemotron 3 Ultra (nvidia/nemotron-3-ultra-550b-a55b) costs $0.6 per 1M prompt tokens and $2.4 per 1M completion tokens, has a 262,144-token context window, and supports tool calling, structured outputs, reasoning and response format. Data updated 2026-10-30.
- Prompt price
- $0.6 / 1M tokens
- Completion price
- $2.4 / 1M tokens
- Context
- 262,144 tokens
- Input modalities
- text
- Output modalities
- text
- Tokenizer
- Other
- Instruct type
- —
- Knowledge cutoff
- —
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Last price change: 2026-10-11
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...