Cost
Filed under
1 post
When Haiku Beats Opus: Model Right-Sizing on Bedrock
Defaulting every call to Opus is how LLM bills balloon. Route by task class: Haiku for the mechanical majority, Opus as the escalation path for hard cases.
Defaulting every call to Opus is how LLM bills balloon. Route by task class: Haiku for the mechanical majority, Opus as the escalation path for hard cases.