↑↓ to navigate Enter to select Esc to close
Try Pro
Setting things up for you...
Drop file here

Custom Instructions

Existing Custom Instructions Found

You have custom instructions from the previous version. Copy them to save before switching to the new format.

Custom instructions will only apply to new conversations. Start a new chat to see the changes in effect.

Your custom instructions are saved on-device only.

GPT-5 Settings

minimal low medium high
Controls depth of reasoning and problem-solving.

Notice: Reasoning effort setting only applies when using the Send button. Sending your message with the Enter key uses Send, fast reply (minimal effort) by default.
When disabled, Enter key sends messages according to reasoning effort setting
low medium high
Controls response detail and length
Artifacts
16

Not sure which one to pick?

For most tasks, we recommend Claude 4 Sonnet or GPT-5. Both are capable general-purpose models with different response styles.

GPT-5 is a set of models with configurable reasoning and verbosity, find these settings by selecting GPT-5 from the model selector, then clicking on the settings icon next to the model selector.

Click the lightning icon in the text field for a quick response when GPT-5 is selected, when minimal reasoning setting is sufficient. The fast reply setting is also applied when using the enter key to send a mesage with GPT-5.

We recommend using GPT-5 when attaching documents, since GPT-5 has the best and most recent file-input support (including support for images, and perceptual understanding of PDFs).

For particularly complex tasks, Claude 4 Opus offers higher reasoning capabilities than Claude 4 Sonnet.

o3 is a (legacy) reasoning model, that is, it outputs thinking tokens before answering, that performs well on math, science and coding problems. GPT-5 is also a reasoning model, and when used with the high reasoning setting is often more capable than o3 according to benchmarks.

Gemini 2.0 Flash is a fast model from Google Deepmind that can run code.

GPT-4o is the previous generation of OpenAI's GPT models and GPT-4o mini is a faster, less capable alternative.

Moderate
Tech
Moderate
Creative

Share chat