Nemotron 3 Ultra (batch) pricing & benchmarks
Nemotron 3 Ultra (batch) is available from NVIDIA at $0.300 per million input tokens and $1.80 per million output tokens ($0.675 blended at 3:1). It accepts up to 512,288 tokens of context. 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...
Pricing
Per million tokens · OpenRouter
Input$0.300
Output$1.80
Blended (3:1)$0.675
Specification
nvidia/nemotron-3-ultra-550b-a55b:batch
Context window512K
Max output—
ReleasedJun 2026
LicenceOpen weights
Modalitiesin:text, out:text
No independently-run benchmark scores are published for Nemotron 3 Ultra (batch) yet. We show nothing rather than reprinting an unverified figure.
Compare Nemotron 3 Ultra (batch)
Nemotron 3 Ultra (batch) vs Qwen3.8 Max
Nemotron 3 Ultra (batch) vs DeepSeek V4 Flash 0731
Nemotron 3 Ultra (batch) vs Claude Opus 5
Nemotron 3 Ultra (batch) vs Gemini 3.6 Flash
Nemotron 3 Ultra (batch) vs Kimi K3
Nemotron 3 Ultra (batch) vs GPT-5.6 Luna
Nemotron 3 Ultra (batch) vs GPT-5.6 Terra
Nemotron 3 Ultra (batch) vs GPT-5.6 Sol
FAQ
How much does Nemotron 3 Ultra (batch) cost?
Nemotron 3 Ultra (batch) costs $0.300 per million input tokens and $1.80 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.675 per million tokens.
What is Nemotron 3 Ultra (batch)'s context window?
Nemotron 3 Ultra (batch) accepts up to 512,288 tokens of context.