gpudiff the public record of change in GPU cloud pricing

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

inkling API price — 4 gateways compared

Cheapest right now: DeepInfra at $0.95/MTok in — 2.0× cheaper than the priciest gateway.

from $0.95 per million input tokens · 2.0× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$0.95	$4.05	524,288	thinkingmachines/inkling	use
Glama	$0.95	$4.05	524,288	thinkingmachines/inkling	use
DeepInfra	$0.95	$4.05	524,288	thinkingmachines/Inkling	use
Requesty	$1.87	$4.68	65,536	thinkingmachines/inkling	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

2026-10-02 openrouter cut thinkingmachines-inkling-input 5.0%: 1.0 → 0.95 usd_per_mtok
2026-08-30 openrouter raised thinkingmachines-inkling-input 5.3%: 0.95 → 1.0 usd_per_mtok
2026-08-27 requesty raised inkling-output 11.1%: 4.212 → 4.68 usd_per_mtok
2026-08-27 requesty raised inkling-input 11.1%: 1.683 → 1.87 usd_per_mtok
2026-08-25 openrouter cut thinkingmachines-inkling-input 5.0%: 1.0 → 0.95 usd_per_mtok
2026-08-24 openrouter raised thinkingmachines-inkling-input 5.3%: 0.95 → 1.0 usd_per_mtok

The cheapest tracked gateway charges $0.95 per million input tokens and $4.05 per million output tokens (DeepInfra). Prices refresh continually.

DeepInfra for input tokens and DeepInfra 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.