For comparison on openrouter DeepSeek v4 Flash is slightly cheaper than Gemma 4 31b, more expensive than Gemma 4 26b, but it does support prompt caching, which means for some applications it will be the cheapest. Excited to see how it compares with Gemma 4.

▲

MillionOClock 2 days ago | parent [-]

I wonder why there aren't more open weights model with support for prompt caching on OpenRouter.

▲

mzl 2 days ago | parent [-]

It is tricky to build good infrastructure for prompt caching.

	▲	jatora 2 days ago \| parent [-]
		Its as simple as telling your claude code to implement prompt caching!