Ok, but why did they chose Sonnet in the first place? Couldn't they have chosen Haiku or GPT Luna or maybe even some small cheap Chinese model?

▲

theshrike79 3 hours ago | parent | next [-]

I’m guessing accuracy. Smaller models are just THAT much more inaccurate to not make it viable.

	▲	psnehanshu 35 minutes ago \| parent [-]
		I think for this purpose a small model will do reasonably well

▲

loafoe 2 hours ago | parent | prev | next [-]

Strands decider actually uses a small cheap/free Chinese model for its base architecture: Qwen

▲

Hamuko 3 hours ago | parent | prev [-]

Not sure if it would even need to be a small Chinese model. Amazon would surely have the necessary hardware and infrastructure to run a bigger Chinese model with a low per-token cost too. They probably get their Sonnet at a discounted rate too since they do the inference "locally", but I imagine the savings for not having to pay Anthropic their share would still add up.