Remix.run Logo
stavros a day ago

Have you guys been having a good experience with OpenRouter? I tried it out recently with Claude, and it cached no tokens, charging me $200 for one conversation of 11 messages.

DefineOutside a day ago | parent | next [-]

I tried using deepseek v4 flash with OpenRouter. It switches between providers too eagerly which resets the cache. Then, each provider begins to rate limit me for providing so many uncached tokens, so it just keeps on switching providers. I'm paying for every token... why rate limit me? It was unusable compared to just using the official Deepseek provider which has a much better cache rate.

eikenberry a day ago | parent [-]

You really need to select your provider with Openrouter to get the best experience.

https://openrouter.ai/docs/guides/routing/provider-selection

akie a day ago | parent | prev [-]

I just checked because I was a bit paranoid, but I have a 96.6% cache hit rate for GPT-5.6 Luna and 96.8% for Opus 5.

stavros a day ago | parent [-]

Hm, thanks, it must have been some OpenWebUI bug, thank you.