Comment by somewhatjustin

7 hours ago

> Claude Sonnet 5.5 and Claude Haiku 5.5 will follow in the coming weeks, with many of the same improvements to performance, efficiency, and safety.

Nice. I was starting to think that Haiku got abandoned.

9 comments

somewhatjustin

Reply
Sol-  7 hours ago

Found this announcement interesting since allegedly OpenAI is retiring their Terra tier. I think for everyday work, two models with various thinking efforts seem enough, plus some frontier level model like Fable or Astra to coordinate.

  • ricardobeat  6 hours ago

    Terra lost to Sol and Luna at every cost/performance point, it had no reason to exist.

    • w-m  1 hour ago

      At introduction, Terra was a good mid-tier model. Terra [high] was on the pareto frontier of DeepSWE's score over cost, if only ever so slightly.

      When I had Sol orchestrate Luna and Terra as implementation agents, Sol was a lot happier with what Terra produced and would find far fewer issues than what was implemented by Luna.

      But a few weeks after introduction, OpenAI slashed Luna's cost by 80% and Terra's only by 20%. Only then did it become uneconomical to run Terra and its reason to exist stopped.

  • skerit  5 hours ago

    Retiring the Terra tier? Their space-inspired lineup has only been out for 2 months, they're already messing with it?

  • somewhatjustin  7 hours ago

    I personally use up to 3 models. Fable/Opus for planning, Opus/Sonnet for implementation depending on complexity.

    I would maybe use Haiku 5.5 for highly parallel workflows like checking in on MRs or scanning my entire codebase.

    • jaapz  4 hours ago

      Only reason I used Haiku was when I made Opus 5 run Haiku agents just to rewrite Opus 5's garbage output into something legible

mchusma  7 hours ago

I hope Haiku is Pareto better than Luna/Deepseek, so slashing its price by about 90%.