NVIDIA: Nemotron 3 Ultra
NVIDIAOpen weights
NVIDIA: Nemotron 3 Ultra by NVIDIA costs $0.60 per 1M input tokens and $2.40 per 1M output tokens, with a 262K-token context window.
Pricing
Input (per 1M tokens)
$0.60
Output (per 1M tokens)
$2.40
Cached input (per 1M)
$0.12
Specifications
- Provider
- NVIDIA
- Context window
- 262K tokens
- Parameters
- 550B
- Released
- Jun 2026
- Open weights
- Yes
- Frontier model
- No
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Benchmarks
- GPQA Diamond
- 85.3
- LiveBench
- 50.7
Speed & latency
Time to first token
0.37s
Output speed
24 tok/s
Fastest host: deepinfra (via hf-router).
Compare NVIDIA: Nemotron 3 Ultra with…
NVIDIA: Nemotron 3 Ultra vs Qwen3.5 Plus$2.40/1MNVIDIA: Nemotron 3 Ultra vs Qwen3.5 27B$2.40/1MNVIDIA: Nemotron 3 Ultra vs QwQ Plus$2.40/1MNVIDIA: Nemotron 3 Ultra vs gemini-2.5-flash-preview-09-2025$2.50/1MNVIDIA: Nemotron 3 Ultra vs Gemini 2.5 Flash$2.50/1MNVIDIA: Nemotron 3 Ultra vs Gemini 3.5 Flash Lite$2.50/1M
FAQ
How much does NVIDIA: Nemotron 3 Ultra cost?
NVIDIA: Nemotron 3 Ultra is priced at $0.60 per 1M input tokens and $2.40 per 1M output tokens. Output tokens cost more than input.
What is NVIDIA: Nemotron 3 Ultra's context window?
NVIDIA: Nemotron 3 Ultra supports a context window of 262K tokens — the maximum prompt plus response length it can handle in a single request.
Is NVIDIA: Nemotron 3 Ultra open weight?
Yes — NVIDIA: Nemotron 3 Ultra has openly available weights.
Data as of 2026-10-15. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.