gpudiff the public record of change in GPU cloud pricing

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

qwen3.8-2.4t-a95b API price — 5 gateways compared

Cheapest right now: DeepInfra at $2.00/MTok in — 1.2× cheaper than the priciest gateway.

from $2.00 per million input tokens · 1.2× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$2.00	$6.00	1,048,576	qwen/qwen3.8-2.4t-a95b	use
Glama	$2.00	$6.00	1,000,000	alibaba/qwen3.8-2.4t-a95b	use
Novita	$2.00	$6.00	1,000,000	qwen/qwen3.8-2.4t-a95b	use
DeepInfra	$2.00	$6.00	262,144	Qwen/Qwen3.8-2.4T-A95B	use
Requesty	$2.50	$6.00	1,000,000	tensorx/qwen3.8-2.4t-a95b	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

The cheapest tracked gateway charges $2.00 per million input tokens and $6.00 per million output tokens (DeepInfra). Prices refresh continually.

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

Yes — the most expensive tracked gateway charges 1.2× the cheapest for input tokens. Identical model, identical tokens, different bill.