News for hackers. Stuff that matters.
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by sparkling on Monday August 03, 2026 @04:52AM (#49153022)
Is it? OpenRouter shows DeepInfra being cheaper than DeepSeek directly

https://openrouter.ai/deepseek/deepseek-v4-flash-20260731#pr...

Re:Qwen3.8-Max: A New Bar for Coding and Cowork by thecopy on Monday August 03, 2026 @04:58AM (#49153066)
I agree with parent. OpenRouter might be cheaper list-price, but i have been using 10$ on DS platform since April/May, still have 2$ left. Using OpenRouter i depleted the same dollar-amount in a 1-2 weeks with same usage pattern. No idea why.
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by sparkling on Monday August 03, 2026 @05:07AM (#49153137)
What does your usage look like?
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by Fluorescence on Tuesday August 04, 2026 @03:29AM (#49165398)
Not used it but from perusing forums, consensus is OpenRouter has terrible/broken caching for Deepseek wildly inflating token use. The cache metrics are visible so you can verify for yourself (apparently, it's what others have done).
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by nimoday on Monday August 03, 2026 @06:54AM (#49154023)
DeepInfra's Cache Read is 6.5 times more expensive than DeepSeek.
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by miroljub on Monday August 03, 2026 @08:00AM (#49154614)
And in many scenarios, cache hits are 99% of tokens, so the price difference in caching really adds up quickly.
Re:Qwen3.8-Max: A New Bar for Coding and Cowork by maattdd on Monday August 03, 2026 @04:58AM (#49153064)
Interesting. My anecdotal experience is that it is.