Using gpt-5.4-mini in off-peak hours already feels like super-speed to me. That's probably no more than 100-150 tk/s. I can't imagine 750!

I've always eyed Cerebras but never had a use for it that would justify paying for the API directly. Although now that I think about it, trying out the API would probably cost less than a subscription for a month...

▲

jasonjmcghee 2 hours ago | parent | next [-]

Try gpt-5.3-codex-spark - it's 1000 TPS and from my experience more capable than 5.4 mini.

If you have a subscription it's a different pool of usage.

▲

small_model 2 hours ago | parent [-]

Used it, very fast but tiny context window and doesn't have good reasoning. (good for quick simple code changes)

▲

beering an hour ago | parent [-]

Agreed, 1000tok/s just fills up the context window (which is big by 2004 standards) super fast. But seems like 5.3-spark was just a taste of what’s to come.

▲

taneq an hour ago | parent [-]

2004 standards? O.o

	▲	partsch 43 minutes ago \| parent [-]
		1904

▲

embedding-shape 3 hours ago | parent | prev | next [-]

The ChatGPT subscription gives you access to the -spark model(s) in Codex which are blazing fast (but pretty dumb) which I think runs on Cerebras hardware too.

▲

kegs_ 3 hours ago | parent | prev [-]

I have a pretty good use case for gpt-oss. The amount of time savings has actually been wild. Definitely worth a try. Just to be clear, it gets like 2000tok/s