GLM 5.2 vs. Opus

Re:GLM 5.2 vs. Opus by faxmeyourcode on Monday June 22, 2026 @12:53PM (#48632706)

I feel like another comparison worth looking at is purely cost.

Capability per dollar is something I care about:

    Opus API    $5/$25
    Sonnet API  $5/$15
    Haiku API   $1/$5

    GLM 5.2 API $1.4/$4.4

So you're really getting near opus level capability for the price of haiku.

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by cmrdporcupine on Monday June 22, 2026 @02:01PM (#48633609)

Not really, GLM uses more tokens to get work done.

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by dymk on Monday June 22, 2026 @03:04PM (#48634557)

By how much? At least TFA provided numbers for one example, and they disagree with you (by a lot).

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by wiremine on Monday June 22, 2026 @02:21PM (#48633892)

I ran a fairly large experiment last week, and the token usage wasn't bad at all. What softs of use cases are you seeing large token usage by GLM 5.2?

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by w0m on Monday June 22, 2026 @04:21PM (#48635585)

> are you seeing large token usage by GLM 5.2

the statement isn't "GLM 5.2 has large token usage", it's "GLM 5.2 has large token usage vs modern Opus".

I haven't used it, but this wouldn't surprise me. I see ~30% lower token usage for better results with Opus 4.8 vs 4.6 (and i had great results with 4.6)

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by cmrdporcupine on Monday June 22, 2026 @07:51PM (#48638184)

I'm comparing with GPT5.5 on Codex and it's not even a competition. GLM takes way longer and eats a lot of tokens getting work done, it's easy to rack up a big bill on openrouter. I tried the $20 plan from ollama, too, and ate through half a month of budget in a few hours and blew my daily limit twice and still had to get codex to complete it -- which it did with only 10% of my monthly limit remaining.

GLM is promising but it's pretty costly, all things considered.

[ Parent | on HN ]

Re:GLM 5.2 vs. Opus by throwawayffffas on Monday June 22, 2026 @05:04PM (#48636174)

In the article, they claim GLM used almost half the tokens 131,000, and the cost is about a quarter. For the cost to be the same GLM would have to use 4-5 times more tokens.

[ Parent | on HN ]