Claude gives you several models to choose from, and the right one isn't always the biggest one. Effort levels, fast mode and subagents add more dials on top, so the choice is rarely just about price. Here's the rule of thumb I use: start with Opus at medium, then move down or up when the task calls for it.
Start with Opus
You should start with the Opus model at its default medium effort level. It costs half as much as Fable and is already selected for you, so it's recommended for most day-to-day tasks. Opus is also a great choice for vision-heavy tasks.
When to Move Down
Move down to Sonnet for well-scoped features and small bug fixes. However, even if a task is well-scoped, that doesn't mean Sonnet is the best model for it. Major refactors or tricky bugs should be handled by larger models. Sonnet models are great for tasks you run repeatedly, such as investigations, reviews or drafts.
Move down to Haiku for high-volume tasks, such as clarification or routing.
Small models are less suited to long agentic loops, though. Use them where mistakes are easy to spot and quick to fix.
When to Move Up
Move up to Fable for the trickiest technical problems. Before you do, though, you could try Opus at high effort. Keep in mind that raising the effort level beyond high can cost as much as using a larger model.
If you move up one model, use a lower effort level than you used with the smaller model.
A higher effort level helps when the model needs to think longer, call more tools or check its own work, but it doesn't give the model knowledge or skills it doesn't have.
Ultracode and Subagents
For fairly complex tasks, you could enable ultracode. It doesn't change the model; it just changes how Claude organizes the work. It automatically plans a workflow for substantial tasks and coordinates subagents when useful.
Subagents run in their own context windows and hand back only a summary. The main model keeps the thread.
Price, Speed and Latency
When choosing a model, price isn't the only trade-off. Bigger models cost more and are more capable, but they have higher latency. Effort level and latency are roughly correlated.
Opus and Fable models have fast mode, which lowers latency without changing their quality or capabilities. One drawback is that it costs more.
A higher price per token doesn't necessarily mean you'll get better results.
Self-verification with tests or scripts on a smaller model can be more cost-effective and quicker than reaching for a bigger one.
Next-generation models are usually not only faster (some by 30%) but also cheaper and more capable.
Cache
There is no read-cache price difference between Opus and Fable models, but writing to the cache costs twice as much with Fable.
Switching models does not transfer the cache; it has to be built from scratch.
Conclusion
Model choice is a habit more than a one-off decision. Start from the default, notice where it struggles and change one dial at a time — model first, then effort. If the smaller model and the bigger one give you the same result, keep the smaller one.