logoalt Hacker News

stavrosyesterday at 4:47 PM2 repliesview on HN

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.


Replies

DefineOutsideyesterday at 6:02 PM

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.

show 1 reply
akieyesterday at 5:57 PM

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.

show 1 reply