gpudiff the public record of change in GPU cloud pricing

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

ling-3.1-flash API price — 2 gateways compared

Cheapest right now: OpenRouter at $0.07/MTok in — 4.0× cheaper than the priciest gateway.

from $0.07 per million input tokens · 4.0× spread between gateways · updated continually

Gateway	$ in /MTok	$ out /MTok	Context	Input price history	Model ID
OpenRouter fees	$0.07	$0.23	262,144	since 2026-10-13	inclusionai/ling-3.1-flash	use
Novita	$0.30	$0.90	262,144	since 2026-10-13	inclusionai/ling-3.1-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

2026-10-13 openrouter listed inclusionai-ling-3.1-flash-output at 0.225 usd_per_mtok
2026-10-13 openrouter listed inclusionai-ling-3.1-flash-input at 0.075 usd_per_mtok
2026-10-13 novita listed ling-3.1-flash-output at 0.9 usd_per_mtok
2026-10-13 novita listed ling-3.1-flash-input at 0.3 usd_per_mtok

The cheapest tracked gateway charges $0.07 per million input tokens and $0.23 per million output tokens (OpenRouter). Prices refresh continually.

OpenRouter for input tokens and OpenRouter for output tokens, among the 2 gateways we track.

Yes — the most expensive tracked gateway charges 4.0× the cheapest for input tokens. Identical model, identical tokens, different bill.