3 comments

• Catloafdev an hour ago

  I know HN sometimes has 'show' posts, but usually they aren't just ads, usually they have _something_ more than just a plain old "hey come spend money on my product" ad. Like a tech write-up, or something.

  This is just an ad.

  [-]
  droidjj an hour ago

  It's also certainly not 2x-4x cheaper than getting GLM 5.3 inference elsewhere.

  Compare: https://www.coralbricks.ai/docs#models vs https://openrouter.ai/z-ai/glm-5.3#providers

• nateb2022 an hour ago

  Your 2x-4x cheaper claim is really hard to verify without transparent pricing for input/cache/output. Seems like you don't want to be easily compared to other providers, like on OpenRouter?

  Edit: some back of the napkin math on GLM 5.2:

    $51.20 for 1B input, 4M output, 98% cache rate
    $303.20 for 1B input, 4M output, 83% cache rate
    $329.60 for 1B input, 10M output, 83% cached
    => $1.68/M input, $0/M cached, $4.40/M output
  

  Which seems more expensive compared to $0.4186/$0.07774/$1.316 in/cache/out on OpenRouter: https://openrouter.ai/z-ai/glm-5.2