Output tokens cost $6.00 per million on grok-4.5 and $0.20 per million on nemotron-lightning-3.5-30b-a3b. Input tokens cost $2.00 per million on grok-4.5 and $0.05 per million on nemotron-lightning-3.5-30b-a3b. Cached input tokens are billed at $0.50 per million on grok-4.5 and $0.01 per million on nemotron-lightning-3.5-30b-a3b. Context lengths are 500,000 tokens on grok-4.5 and 262,000 tokens on nemotron-lightning-3.5-30b-a3b. Time to first token (TTFT) measured on AIHubMix is 2.2s on grok-4.5 and 0.2s on nemotron-lightning-3.5-30b-a3b. Measured output throughput is 41.6 tok/s on grok-4.5 and 108.1 tok/s on nemotron-lightning-3.5-30b-a3b.
grok-4.5
nemotron-lightning-3.5-30b-a3bGrok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and math. With both intelligent and efficient reasoning, Grok 4.5 excels at real engineering tasks and exceeds comparable leading models at these tasks.
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, featuring 3 billion active parameters out of 30 billion total. It supports an extensive context window of up to 1,000,000 tokens. This model is designed to deliver efficient performance for high-throughput agentic workloads and specialized tasks. Compared with Nemotron 3 Super and Ultra, Lightning is smaller and optimized for fast, high-volume execution, while the larger models focus on complex planning and advanced reasoning.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
nemotron-lightning-3.5-30b-a3b: $0.20/M output tokens; grok-4.5: $6.00/M. Use the cost calculator above to estimate your own workload.
nemotron-lightning-3.5-30b-a3b: 0.2s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
grok-4.5 accepts 500,000 and nemotron-lightning-3.5-30b-a3b accepts 262,000 input tokens.
nemotron-lightning-3.5-30b-a3b at 108.1 tok/s and grok-4.5 at 41.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
grok-4.5 accepts text and image input and supports thinking, tool calling, function calling, structured outputs and long context; nemotron-lightning-3.5-30b-a3b accepts text input and supports reasoning, tool calling and long context.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix