sridhar
@RamaswmySridhar
623 Following 35.3K Followers
But here's the punchline.
Normalized to 90% cache hit rate:
GLM-5.2 (Fireworks): $1.12/session
Opus-4.7 (Anthropic): $2.14/session
GLM is ~48% cheaper.
Follow-up to my GLM vs Opus thread: let's talk cost.
We ran 103 dbt tasks x 3 trials on each model. Same harness, same tasks.
GLM: 860M tokens
Opus: 439M tokens
That's ~2x. But the "why" is more interesting than the number.
Show more
