NVIDIA Nemotron 3 Ultra Benchmarks, Pricing & Rankings
NVIDIA · 2026-06-04 · Open · Current
Snapshot 2026-11-06 · updated weekly
NVIDIA Nemotron 3 Ultra ranks #11 of 71 on the AMR leaderboard.
NVIDIA Nemotron 3 Ultra benchmark scores
NVIDIA Nemotron 3 Ultra price, speed & context
Input price
$0.60
per 1M tokens
OpenRouter rate card · 2026-10-30
Output price
$2.40
per 1M tokens
Speed
—
tok/s
Context
262K
tokens
About NVIDIA Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is the open frontier-reasoning and orchestration model of the Nemotron 3 family: 550B total MoE with 55B active parameters, 262K context, $0.60/$2.40 per million tokens on OpenRouter, ranked 11th by weekly token volume. AMR score is an anchor estimate off board rank pending independent benchmarks; throughput readings not yet recorded.
Models around NVIDIA Nemotron 3 Ultra in the rankings
More NVIDIA models
NVIDIA Nemotron 3 Ultra FAQ
Where does NVIDIA Nemotron 3 Ultra rank?
NVIDIA Nemotron 3 Ultra ranks #11 of 71 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 80.3. Its strongest dimension is AMR at 80.3.
How much does NVIDIA Nemotron 3 Ultra cost?
NVIDIA Nemotron 3 Ultra costs $0.60 per million input tokens and $2.40 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $1.95 per million tokens.
What is the NVIDIA Nemotron 3 Ultra context window?
NVIDIA Nemotron 3 Ultra supports a 262K token context window and generates at a median 0 output tokens per second. That context fits roughly 175 standard documents in a single prompt.
Is NVIDIA Nemotron 3 Ultra open source?
Yes — NVIDIA Nemotron 3 Ultra ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than NVIDIA Nemotron 3 Ultra?
GPT-6.1 Terra ranks one place higher at #10 with an AMR score of 80.5. NVIDIA Nemotron 3 Ultra still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.