# Choosing model, effort and fast mode Model, effort and fast mode are three separate dials. Each one changes what a turn costs and how long it takes, and two of them reset the cache if you turn them mid-task. ## Three dials, not one People talk about "using the strong model" as if it were a single choice. In Claude Code it is three, and they are independent. **Model** decides who is thinking. **Effort** decides how hard that model is asked to think on a turn. **Fast mode** decides how quickly the same model answers, and at what price. Setting each one for the right reason is worth more than always turning all of them up. ## The model You pick a model with an alias, and aliases move forward over time. The list is `default`, `best`, `fable`, `sonnet`, `opus`, `haiku`, plus `sonnet[1m]` and `opus[1m]` for the one-million-token window, and `opusplan`. If you need a model that never changes under you, pin a full model ID instead of an alias. `opusplan` uses opus while planning and sonnet while executing. It is a good fit for the work, and you should know the cost: every plan-mode toggle becomes a model switch, and a model switch resets the cache. The order in which a choice is applied runs from your most recent decision to the most general one: `/model` inside the session, `--model` at startup, the `ANTHROPIC_MODEL` variable, the `model` key in settings, and `ANTHROPIC_DEFAULT_MODEL`. ```terminal $ claude --model sonnet * Starts the session on Sonnet $ /model fable * Switches the running session to Fable # The guide names Opus 5.5 at medium effort as the default. Fable 5.1 is chosen explicitly. ``` **Question:** Why can a mid-session /model switch make the next turn slower and costlier? - The new model is always larger - Each model has its own cache, so the conversation is read uncached - Switching deletes CLAUDE.md - The window is cleared **Answer:** Each model has its own cache, so the conversation is read uncached. The prompt cache belongs to one model. After a switch the whole conversation has to be processed again before caching resumes. ## Effort and thinking The effort levels are low, medium, high, xhigh and max, and the command line also accepts ultracode. You set it with `/effort` or `--effort`. The guide's advice reads like a ladder: - `medium` for everyday work. - `high` or `xhigh` for subtle bugs and schema changes. - `low` for quick back and forth. - `max` only for hard, unattended problems, because it tends to overthink. - `ultrathink` in a single prompt for one tricky question. The guide is explicit that phrases like "think step by step" are plain text, not keywords. Effort is the real control. The one wording that still helps is "be ambitious", because it signals scope rather than thinking depth. > **Some models always think** On Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable, extended thinking is always on. The toggle (`Option+T`) has no effect on them, and `MAX_THINKING_TOKENS` only affects models with a fixed budget. Thinking tokens bill as output. On those models, changing effort keeps the cache. On most others it does not. ## Fast mode Fast mode makes Opus up to 2.5 times faster, at a higher price per token. The documented figures are 8 and 40 USD per million input and output tokens on Opus 5.5. It is not a different model. It is the same one, served faster, which is exactly why it has a separate cache. On subscription plans it is billed through usage credits, not plan limits. A small lightning icon shows while it is on. `/fast` toggles it, and the setting `fastMode: true` persists it. Timing matters here as much as in the cache lesson. If you turn it on mid-turn, the running turn finishes at normal speed. If you turn it on mid-session, the first enable reads the whole conversation uncached at fast rates. Turn it on at the start or not at all. **Question:** What is fast mode? - A smaller, cheaper model - The same Opus model served up to 2.5x faster at a higher per-token price - A lower effort level - A setting that skips tool calls **Answer:** The same Opus model served up to 2.5x faster at a higher per-token price. Fast mode changes speed and price, not the model. That is also why it has its own prompt cache. ## A way to decide Choose at the start, and choose by the task. ```flow Start of session: pick model and effort Routine edits and questions: medium effort Hard bug, or schema change: raise effort once Need speed, and budget allows: fast mode, from the start Stuck after two corrections: /clear, not a bigger model ``` The last line is the point of this whole course. A bigger dial does not fix a window full of the wrong things. When an answer is poor, look at the context first. If you want a second opinion, `/advisor` or `--advisor ` lets a stronger model advise the session. > **Spend effort on purpose** Take a task you would normally leave at the default. Ask for it once at `low` and once at `high` in fresh sessions. Compare the answer and what `/usage` says. You will learn where your own work sits on the ladder.