gpudiff the public record of change in GPU cloud pricing

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

Gemini 3.7 Flash API price — 4 gateways compared

Cheapest right now: Glama at $0.38/MTok in — 2.0× cheaper than the priciest gateway.

Google · from $0.38 per million input tokens · 2.0× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
Glama	$0.38	$1.88	1,048,576	google/gemini-3.7-flash	use
OpenRouter fees	$0.75	$3.75	1,048,576	google/gemini-3.7-flash	use
Requesty	$0.75	$3.75	1,048,576	vertex/gemini-3.7-flash	use
DeepInfra	$0.75	$3.75	1,000,000	google/gemini-3.7-flash	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

2026-08-29 openrouter listed google-gemini-3.7-flash-output at 3.75 usd_per_mtok
2026-08-29 openrouter listed google-gemini-3.7-flash-input at 0.75 usd_per_mtok
2026-08-28 openrouter delisted google-gemini-3.7-flash-output
2026-08-28 openrouter delisted google-gemini-3.7-flash-input
2026-08-27 requesty raised gemini-3.7-flash-output 25.0%: 3.0 → 3.75 usd_per_mtok
2026-08-27 requesty raised gemini-3.7-flash-input 25.0%: 0.6 → 0.75 usd_per_mtok

The cheapest tracked gateway charges $0.38 per million input tokens and $1.88 per million output tokens (Glama). Prices refresh continually.

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

Yes — the most expensive tracked gateway charges 2.0× the cheapest for input tokens. Identical model, identical tokens, different bill.