gpudiff the public record of change in GPU cloud pricing

Follow the diffs: RSS · Free API · Sponsor this site

nemotron-3-nano-30b-a3b API price — 4 gateways compared

from $0.05 per million input tokens · same price on every gateway · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$0.05	$0.20	262,144	nvidia/nemotron-3-nano-30b-a3b	use
Requesty	$0.05	$0.20	262,144	deepinfra/nvidia/Nemotron-3-Nano-30B-A3B	use
Glama	$0.05	$0.20	262,144	nvidia/nemotron-3-nano-30b-a3b	use
Novita	$0.05	$0.20	262,144	nvidia/nemotron-3-nano-30b-a3b	use

Fees beyond the token price

OpenRouter: No markup on token prices (provider pass-through), but credit purchases cost 5.5% via card ($0.80 minimum) or 5% via crypto; BYOK usage above the monthly allowance is charged 5%. source

2026-09-21 openrouter cut nvidia-nemotron-3-nano-30b-a3b-output 16.7%: 0.24 → 0.2 usd_per_mtok
2026-09-21 openrouter cut nvidia-nemotron-3-nano-30b-a3b-input 16.7%: 0.06 → 0.05 usd_per_mtok
2026-09-17 openrouter raised nvidia-nemotron-3-nano-30b-a3b-output 20.0%: 0.2 → 0.24 usd_per_mtok
2026-09-17 openrouter raised nvidia-nemotron-3-nano-30b-a3b-input 20.0%: 0.05 → 0.06 usd_per_mtok
2026-08-27 requesty raised nemotron-3-nano-30b-a3b-output 11.1%: 0.18 → 0.2 usd_per_mtok
2026-08-27 requesty raised nemotron-3-nano-30b-a3b-input 11.1%: 0.045 → 0.05 usd_per_mtok

The cheapest tracked gateway charges $0.05 per million input tokens and $0.20 per million output tokens (Glama). Prices refresh continually.

Glama for input tokens and Glama for output tokens, among the 4 gateways we track.

No — every tracked gateway currently charges the same per-token price, so the difference between them is fees and routing, not token cost.