Model Picker

Answer a few quick questions and get the right Claude model, effort level and cost-saving features for your use case — with a monthly cost estimate and starter code.

Step 1 of 6: Task

What will Claude mostly do?

Your recommendation

Answer the questions to see a recommendation. It updates live as you change your answers.

Claude Haiku 5.5$0.1 / $0.5 per 1M tokensThe fastest and cheapest — ideal for high-volume classification, extraction and simple chat.

Claude Sonnet 5.5$2 / $10 per 1M tokensFast and capable — the balanced choice for everyday coding, chat and enterprise work.

Claude Opus 5.5$4 / $20 per 1M tokensThe default high-quality model: excellent at coding, agents, analysis and writing.

Claude Fable 5.2$8 / $40 per 1M tokensAnthropic's most capable widely released model — for the hardest reasoning and long-horizon agentic work.