gpudiff the public record of change in GPU cloud pricing

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

gemma-4-31b-it API price — 5 gateways compared

Cheapest right now: OpenRouter at $0.09/MTok in — 1.7× cheaper than the priciest gateway.

from $0.09 per million input tokens · 1.7× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$0.09	$0.34	262,144	google/gemma-4-31b-it	use
Glama	$0.10	$0.34	262,144	google/gemma-4-31b-it	use
Requesty	$0.13	$0.38	262,144	deepinfra/google/gemma-4-31B-it	use
Novita	$0.14	$0.40	262,144	google/gemma-4-31b-it	use
DeepInfra	$0.15	$0.40	262,144	google/gemma-4-31B-it	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

2026-10-01 deepinfra raised gemma-4-31b-it-output 5.3%: 0.38 → 0.4 usd_per_mtok
2026-10-01 deepinfra raised gemma-4-31b-it-input 15.4%: 0.13 → 0.15 usd_per_mtok
2026-08-27 requesty raised gemma-4-31b-it-output 11.1%: 0.342 → 0.38 usd_per_mtok
2026-08-27 requesty raised gemma-4-31b-it-input 11.1%: 0.117 → 0.13 usd_per_mtok
2026-08-26 openrouter cut google-gemma-4-31b-it-input 10.0%: 0.1 → 0.09 usd_per_mtok
2026-08-21 openrouter raised google-gemma-4-31b-it-input 11.1%: 0.09 → 0.1 usd_per_mtok
2026-08-20 openrouter cut google-gemma-4-31b-it-input 10.0%: 0.1 → 0.09 usd_per_mtok

The cheapest tracked gateway charges $0.09 per million input tokens and $0.34 per million output tokens (OpenRouter). Prices refresh continually.

OpenRouter for input tokens and Glama for output tokens, among the 5 gateways we track.

Yes — the most expensive tracked gateway charges 1.7× the cheapest for input tokens. Identical model, identical tokens, different bill.