gpudiff the public record of change in GPU cloud pricing

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

qwen3.5-122b-a10b API price — 3 gateways compared

Cheapest right now: Glama at $0.26/MTok in — 1.5× cheaper than the priciest gateway.

from $0.26 per million input tokens · 1.5× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Model ID
OpenRouter fees	$0.26	$2.08	262,144	qwen/qwen3.5-122b-a10b	use
Glama	$0.26	$2.08	262,144	alibaba/qwen3.5-122b-a10b	use
Novita	$0.40	$3.20	262,144	qwen/qwen3.5-122b-a10b	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

2026-09-10 openrouter cut qwen-qwen3.5-122b-a10b-output 13.3%: 2.4 → 2.08 usd_per_mtok
2026-09-10 openrouter cut qwen-qwen3.5-122b-a10b-input 10.3%: 0.29 → 0.26 usd_per_mtok
2026-08-28 openrouter raised qwen-qwen3.5-122b-a10b-output 15.4%: 2.08 → 2.4 usd_per_mtok
2026-08-28 openrouter raised qwen-qwen3.5-122b-a10b-input 11.5%: 0.26 → 0.29 usd_per_mtok
2026-08-19 openrouter cut qwen-qwen3.5-122b-a10b-output 13.3%: 2.4 → 2.08 usd_per_mtok
2026-08-19 openrouter cut qwen-qwen3.5-122b-a10b-input 10.3%: 0.29 → 0.26 usd_per_mtok

The cheapest tracked gateway charges $0.26 per million input tokens and $2.08 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 1.5× the cheapest for input tokens. Identical model, identical tokens, different bill.