gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

nemotron-3-super-120b-a12b API price — 3 gateways compared

from $0.09 per million input tokens · 3.5× spread between gateways · updated hourly

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
OpenRouter fees$0.09$0.401,000,000nvidia/nemotron-3-super-120b-a12b
Glama$0.09$0.40262,144since 2026-08-20nvidia/nemotron-3-super-120b-a12b
Requesty$0.30$0.90128,000since 2026-08-20nebius/nvidia/nemotron-3-super-120b-a12b

Fees beyond the token price

Changelog for nemotron-3-super-120b-a12b

nemotron-3-super-120b-a12b pricing FAQ

How much does nemotron-3-super-120b-a12b cost per million tokens?

The cheapest tracked gateway charges $0.09 per million input tokens and $0.40 per million output tokens (Glama). Prices refresh hourly.

Which gateway is cheapest for nemotron-3-super-120b-a12b?

Glama for input tokens and Glama for output tokens, among the 3 gateways we track.

Do nemotron-3-super-120b-a12b prices differ between gateways?

Yes — the most expensive tracked gateway charges 3.5× the cheapest for input tokens. Identical model, identical tokens, different bill.

← All LLM prices · API