‹ BackHN Continuity

Thread

GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price

1066 points · 953 comments · crorella

  1. minimaxir · · focus · HN ↗
    > Cached input costs just $0.10 per million tokens—95% less than standard input pricing and 50% less than GPT‑6 Sol’s cached input pricing

    This is the actual big announcement. 50% cheaper cache than GPT-6 Sol will get you far more mileage on Codex.

    1. joshstrange · · focus · HN ↗
      > 50% cheaper cache than GPT-6 Sol will get you far more mileage on Codex.

      Cache doesn't help you much when you are compacting every 5 minutes...

      I was shocked at how quickly I ran out my $100/mo subscription with a single agent (sol medium).

      1. onlyrealcuzzo · · focus · HN ↗
        If you're compacting every 5 minutes, you have a workflow problem - period.

        No LLM will be cost effective if it's compacting this often. You have to find a way around it.

        1. ngruhn · · focus · HN ↗
          Context window is only 275k or something. And honestly compaction is not that bad in Codex. I often don't even notice I went through 5 compactions in a session.
          1. SyneRyder · · focus · HN ↗
            Sounds like that's the problem then, 275k is a tiny context window. I regularly have sessions that go to 450k or even up to 700k for an unattended overnight Claude Opus session.

            Apparently OpenAI makes you manually setup their 1 Million context window, and it seems to be only documented on X:

            <a href="https:&#x2F;&#x2F;x.com&#x2F;thsottiaux&#x2F;status&#x2F;2089082893804896524" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;thsottiaux&#x2F;status&#x2F;2089082893804896524

            There&#x27;s at least a forum thread about it here:

            <a href="https:&#x2F;&#x2F;community.openai.com&#x2F;t&#x2F;why-does-codex-report-a-258-400-token-context-window-for-gpt-5-6-sol&#x2F;1394346&#x2F;5" rel="nofollow">https:&#x2F;&#x2F;community.openai.com&#x2F;t&#x2F;why-does-codex-report-a-258-4...

            1. gf000 · · focus · HN ↗
              But that 250k context worth way more than 1M in terms of how well it&#x27;s utilized, so actually I do like codex trying to keep you at that sweet spot.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.