Model Picker Wizard
Answer six quick questions about your workload and get a recommended model tier, example models, and the reasoning behind the pick. Updates live as you click.
Your workload
1. What is the main task?
2. Quality vs cost: what wins?
3. How latency-sensitive is it?
4. How much context per request?
5. Request volume?
6. Input modality?
Recommendation
How to read this: the tier matters more than the exact model name. Frontier models give the best reasoning, coding, and long-context quality at the highest price. Balanced models handle most production workloads at a fraction of the cost. Fast-and-cheap models shine for high-volume, well-scoped tasks like extraction, routing, and classification. A common production pattern is to route easy requests to a cheap model and escalate hard ones to a frontier model. Non-Claude examples are approximate peers; check each provider's current lineup and pricing before committing.