Skip to Main Content
Economicsecon-015P1

Tiered model routing based on prompt complexity.

Routing 70% of queries to Haiku…Routing 70% of queries to Haiku ($0.25/MTok) and 30% to Opus ($15/MTok) reduces average cost by 45% compared to Opus-only, with only 2% quality degradation.

Context & Methodology

Without complexity-based routing, every query — including trivial classification and formatting tasks — hits the most expensive model tier, wasting 60x on tasks that a cheap model handles identically.

Applicable Use Cases

workflow

Applies To

openaianthropicgoogle

Primary Impact

cost

Confidence Level

High

Platform Status

Planned

Implementation Effort

high

Recommendation

follow

Execution Priority

P1

Dependencies & Conflicts

Depends on:

Put This Evidence to Work

Use the STCO framework to implement findings like this in structured, testable prompts.

Structured prompts reduce HITL review time from 5 minutes to 45 seconds per item (85% reduction), saving an estimated $6.Scale AI, 'The State of AI Data' annual report, 20…