AI Model Selector
Answer three questions and get the model to use, right down to the tier and version. Opinionated and model-agnostic, and always worth confirming with your own eval.
What are you building?
What matters most?
Your existing cloud or stack?
—
—
Pick the tier first, then the version
Every major provider ships three tiers. A frontier model (Claude Opus, a flagship GPT, Gemini Pro) for the hardest reasoning, coding, and agents. A balanced model (Claude Sonnet, a GPT mini tier, Gemini Flash) that handles most production work at a fraction of the cost. And a fast, cheap model (Claude Haiku, a GPT nano tier, Gemini Flash-Lite) for high-volume, simple tasks. Most products use more than one: a cheap model for the easy steps and a frontier model only where it earns its price.
Version numbers move quickly, so treat the names here as current as of early 2026 and confirm the latest in each provider's docs. The tiers are stable, which is why choosing the tier is the durable decision. The full reasoning is in choosing an LLM for your business, with head-to-heads in Claude vs GPT and Claude vs Gemini. To run a cheap model first and escalate, see multi-model architecture, and to estimate the bill, use the LLM cost calculator.
Built by Deepanshu Grover, a Growth Product Manager and AI builder in Paris. Runs entirely in your browser, nothing is sent anywhere. About · Get in touch