gpudiff the public record of change in GPU cloud pricing

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

minimax-m2.5 API price — 4 gateways compared

Cheapest right now: Glama at $0.22/MTok in — 1.4× cheaper than the priciest gateway.

from $0.22 per million input tokens · 1.4× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
Glama	$0.22	$0.90	196,608	minimax/minimax-m2.5	use
OpenRouter fees	$0.27	$1.08	204,800	minimax/minimax-m2.5	use
Requesty	$0.28	$1.10	196,608	inceptron/minimax-m2.5	use
Novita	$0.30	$1.20	204,800	minimax/minimax-m2.5	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

2026-08-27 requesty raised minimax-m2.5-output 11.1%: 0.99 → 1.1 usd_per_mtok
2026-08-27 requesty raised minimax-m2.5-input 11.1%: 0.252 → 0.28 usd_per_mtok
2026-08-22 openrouter raised minimax-minimax-m2.5-output 13.7%: 0.95 → 1.08 usd_per_mtok
2026-08-21 openrouter raised minimax-minimax-m2.5-output 5.6%: 0.9 → 0.95 usd_per_mtok
2026-08-21 openrouter raised minimax-minimax-m2.5-input 20.0%: 0.225 → 0.27 usd_per_mtok
2026-08-19 openrouter raised minimax-minimax-m2.5-input 2.3%: 0.22 → 0.225 usd_per_mtok

The cheapest tracked gateway charges $0.22 per million input tokens and $0.90 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 1.4× the cheapest for input tokens. Identical model, identical tokens, different bill.