← Back to context Comment by scosman 18 hours ago Or better: Qwen 2.8 27b 2 comments scosman Reply RussianCow 18 hours ago Unfortunately, the lack of an input cache discount makes it prohibitively expensive for most use cases that aren't one-shot prompts. scosman 15 hours ago well same applies to GPT OSS 120. Qwen is just the much smarter model of the 2 public options on Cerebras.
RussianCow 18 hours ago Unfortunately, the lack of an input cache discount makes it prohibitively expensive for most use cases that aren't one-shot prompts. scosman 15 hours ago well same applies to GPT OSS 120. Qwen is just the much smarter model of the 2 public options on Cerebras.
scosman 15 hours ago well same applies to GPT OSS 120. Qwen is just the much smarter model of the 2 public options on Cerebras.
Unfortunately, the lack of an input cache discount makes it prohibitively expensive for most use cases that aren't one-shot prompts.
well same applies to GPT OSS 120. Qwen is just the much smarter model of the 2 public options on Cerebras.