On the web, you can change to your preferred model by selecting the model dropdown in the bottom right corner of the prompt input box. Select Custom, then choose the model you want from the model section, along with the reasoning and speed options.
If no model is selected, the dropdown is labeled Best, which lets Perplexity automatically pick a suitable model for your query. For the full list of models available on your plan, see What advanced AI models are included in my subscription?.
Why did a different model answer?
Perplexity can answer with a different model than the one you selected. Perplexity reroutes the request so you still get an answer instead of an error. In the Perplexity mobile apps, you may see a message that names the model that was used instead. Common reasons include:
The selected model is temporarily unavailable.
The selected model doesn’t apply to that specific request.
You reached a usage limit. On Pro, access to advanced models may be limited during weeks of especially heavy usage, and some models have usage limits on other plans too. Perplexity uses another model until access recovers.
There is no setting that prevents Perplexity from answering with another model when your selected model can’t be used.
Check which model answered
The model shown in the selector before you send a prompt isn’t always the model that answered. On the web, select the three-dot menu below an answer, then select Rewrite to open the model list. The model that answered is preselected. This doesn’t always identify the exact model: if you selected Best, or the answer came from a model that isn’t in the list, the list shows Best.
To get a new answer from a different model, choose it in the list, then select the Rewrite button at the bottom of the list.