Model Routing

Get Started for Real
D

Model routing rules

priority-ordered
1
Code generation → Sonnet
TASK_TYPE= code
claude-3-5-sonnetgpt-4o
2
Long context → 4o-mini
QUERY_LENGTH_GT= 6000 tokens
gpt-4o-minigpt-4o
3
Legal / compliance → 4o
KEYWORD= contract, clause, liability
gpt-4oclaude-3-5-sonnet
4
Everything else → cheapest
ALWAYS
gpt-4o-minillama-3.1-70b

Test routing

Click a prompt to see which model the router picks — and why:

Cut model spend with intelligent routing

This is the real interface — with your own keys it runs on live models, your data, and your team. Start a free 14-day trial (no credit card) or estimate your cost first.