gpudiff the public record of change in GPU cloud pricing

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

gemini-3.8-flash API price — 3 gateways compared

Cheapest right now: Glama at $0.75/MTok in — 1.1× cheaper than the priciest gateway.

from $0.75 per million input tokens · 1.1× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
Requesty	$0.75	$3.75	1,048,576	vertex/gemini-3.8-flash	use
Glama	$0.75	$3.75	1,048,576	google/gemini-3.8-flash	use
OpenRouter fees	$0.82	$4.12	1,048,576	google/gemini-3.8-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

2026-10-15 openrouter raised google-gemini-3.8-flash-output 10.0%: 3.75 → 4.125 usd_per_mtok
2026-10-15 openrouter raised google-gemini-3.8-flash-input 10.0%: 0.75 → 0.825 usd_per_mtok
2026-09-11 glama listed gemini-3.8-flash-output at 3.75 usd_per_mtok
2026-09-11 glama listed gemini-3.8-flash-input at 0.75 usd_per_mtok
2026-09-02 requesty listed gemini-3.8-flash-output at 3.75 usd_per_mtok
2026-09-02 requesty listed gemini-3.8-flash-input at 0.75 usd_per_mtok
2026-09-02 openrouter listed google-gemini-3.8-flash-output at 3.75 usd_per_mtok
2026-09-02 openrouter listed google-gemini-3.8-flash-input at 0.75 usd_per_mtok

The cheapest tracked gateway charges $0.75 per million input tokens and $3.75 per million output tokens (Glama). Prices refresh continually.

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

Yes — the most expensive tracked gateway charges 1.1× the cheapest for input tokens. Identical model, identical tokens, different bill.