Please do not try to use gpt-oss-120b over Cerebras. It is broken, screws up tool calls most of the time, forgets to end thinking blocks and has all sorts of other issues. The speed is amazing but it is absolutely not worth it, especially at that quite incredible cost. Think: $5–10/minute levels of cost with a single agent, because Cerebras also offers no cache pricing for input tokens at all.
Yea i had some pretty meh results using gpt-oss-120b it in my evals where it should have benefited speed alot but it really under performed what i was expecting.
Which is wild because it does, in fact, do caching