Thread

1. spike021 · 1789611283 · focus · HN ↗

   Say I'm using Claude Code or GPT Codex's harnesses but also sending some queries to the respective Anthropic and OpenAI models via OpenRouter.

   Do harnesses and therefore sending the queries directly to the LLM providers have caching and other benefits that OpenRouter does not provide? Would I get any of those benefits if I simply proxied any requests to the major providers' harnesses through OpenRouter? Or only if the requests go straight from the harness to the provider's API?

   1. CaveTech · 1789617417 · focus · HN ↗

      Your question is worded kind of confusingly, but all caching is handled on the inference layer, and by all major providers. In short, caching should work as long as you are sending requests to the same model and provider.

      1. spike021 · 1789619850 · focus · HN ↗

         Apologies. I guess my main question is just is there a benefit to routing directly to a provider through its own harness vs just sending chat requests to those providers using OpenRouter or similar as a proxy?

         As per your response it sounds like at least caching would happen for any provider regardless of the request's origin.

   2. grave0x · 1790304777 · focus · HN ↗

      <a href="https:&#x2F;&#x2F;github.com&#x2F;grave0x&#x2F;statepod-open" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;grave0x&#x2F;statepod-open

      Its literally me realizing they don&#x27;t have a good solution for it. Context should be local. It saves money and potential LLM confusion.

      Plus i can foresee a bunch of other deterministic context and session handling being just plain unrealized due to the default we have currently

Unofficial Hacker News client; not affiliated with Y Combinator.