Model pricing

Model price comparison

Compare model input, output, and cached token costs to choose a safer routing policy for AI API workloads.

Routing tier	Input / 1M	Cached / 1M	Output / 1M	Best fit
Economy	$0.60	$0.08	$2.40	Routine requests
Balanced	$1.20	$0.15	$5.00	Most production workloads
Advanced	$2.50	$0.30	$10.00	Harder tasks with tighter controls
Premium	$5.00	$0.60	$20.00	Short, high-value runs

Use lower-cost tiers for routine work, cap output tokens for coding agents, and reserve premium tiers for short high-value requests.