Model Selector
Pick the model for the task, see the trade-off
A single default model is wrong for half your tasks — overkill for a quick reword, underpowered for a hard debug — yet the choice is hidden in settings, if it exists at all. Model Selector surfaces the engine as a per-task control: a small set of named models with their speed, cost, and strengths, switchable in one move, with a sensible default so picking is optional, not required. Consumer chat is moving the other way — ChatGPT's June 2026 redesign swapped named models for an effort slider — so the pattern's home is now power-user and developer surfaces, where the trade-off must stay visible because someone is paying for it. That drift strengthens the case, not weakens it: when the picker disappears, cost and capability visibility disappear with it.
Framing
The problem
A single default model is wrong for half your tasks — overkill for the quick ones, underpowered for the hard ones — but the choice is hidden in settings, if it exists at all, and consumer products are now removing it entirely.
The pattern
Surface the model as a per-task control — a small set of named models with their speed, cost, and strengths, switchable in one move — a control whose home is now power-user and developer surfaces, where the trade-off has to stay visible.
Why chat breaks here
Chat picks one model behind the scenes — and consumer chat is doubling down, ChatGPT's June 2026 redesign swapped named models for an effort slider — so when the picker goes, cost and capability visibility go with it.
Risks
Too many models is choice overload, and exposing raw model names without their trade-offs just moves the guesswork onto the user.
Avoid when
One model genuinely serves every task, or the audience is mainstream consumers better served by an effort dial than an engine list — the direction ChatGPT took in June 2026.
Use when
Tasks vary from trivial to hard, so a single default model is wrong for most of them — and the cost/speed/capability trade-off should be the user's to make.
DOPE evaluation
- Directability
- Pick the model per task or set a default — fast and cheap, or slow and capable
- Observability
- The active model and its trade-offs — speed, cost, context, strengths — are visible before you run
- Predictability
- The same model gives the same class of result; switching is explicit, never a silent swap
- Explainability
- Each model card states what it is good at and what it trades away, so the pick is informed
In the wild
- ChatGPT · Model picker (now an effort slider) (OpenAI) — Long the canonical named-model picker — until the June 2026 redesign replaced it with a speed-vs-depth slider (Instant to Extra High) that deliberately hides model names and shows no cost. The biggest consumer product is moving away from this pattern, toward an abstracted effort dial.
- Claude · Model selector (Anthropic) — A dropdown of named models (Haiku, Sonnet, Opus) framed by use case — fast versus capable — with a sensible default. The speed/strength trade-off is visible; cost is not shown in the UI.
- Cursor · Model dropdown (Cursor) — Named models plus an Auto toggle, switchable per task. But no cost or speed meters in the picker itself — showing pricing there is an open feature request — so the "see the trade-off" half is still missing here.
- OpenRouter · Model catalog (OpenRouter) — Per-model cost, throughput, and context length side by side, with a compare view. The strongest trade-off-visibility example — though it lives on browsing pages rather than inline in a single pick flow.
FAQ
When should I use the Model Selector pattern?
Tasks vary from trivial to hard, so a single default model is wrong for most of them — and the cost/speed/capability trade-off should be the user's to make.
When should I avoid the Model Selector pattern?
One model genuinely serves every task, or the audience is mainstream consumers better served by an effort dial than an engine list — the direction ChatGPT took in June 2026.
What problem does Model Selector solve?
A single default model is wrong for half your tasks — overkill for the quick ones, underpowered for the hard ones — but the choice is hidden in settings, if it exists at all, and consumer products are now removing it entirely.
Why is chat the wrong fit for this?
Chat picks one model behind the scenes — and consumer chat is doubling down, ChatGPT's June 2026 redesign swapped named models for an effort slider — so when the picker goes, cost and capability visibility go with it.