alt Hacker NewsI hope cheaper inference eventually means faster speeds at the lower tiers. I don't want to settle for 100 t/s, but I don't want to pay $10 per prompt either
Replies
esafak • yesterday at 11:26 PM
GLM 5.2 has a Fast variant at 200-400 tps.
I hope cheaper inference eventually means faster speeds at the lower tiers. I don't want to settle for 100 t/s, but I don't want to pay $10 per prompt either
GLM 5.2 has a Fast variant at 200-400 tps.
Which raises the question, which are the fastest frontier models? are the enterprise hosted Anthropic models faster than what Anthropic serves?
Somehow no one talks about LLM speed.