← All features

Chat

Pick the model. Keep the context. Finish the work.

Choose the model for each chat. Projects keep files and memory in scope, canvas opens beside the thread, and voice and web search are available from the composer.

You choose the modelProjects keep chats, files, and memory togetherCanvas opens beside the threadVoice and search stay in reach
One workspace
ModelMemoryCanvasVoice

Operating model

Defaults, chats, and projects each have their place.

Your defaults, your active chat, and your projects are set separately, so project work stays with the project.

  1. 1

    Set your baseline once.

    Save instructions, tone, profile details, response font, personas, and voice settings so new chats do not start from scratch.

  2. 2

    Choose the active chat setup.

    Pick the model, attach a persona, turn tools on, and decide whether the work belongs in your global stream or inside a project.

  3. 3

    Work from the same surface.

    Search the web, open canvas, attach files, use voice, or keep drafting without hopping across separate products.

Account

Account controls

Set defaults here: custom instructions, profile details, personas, response font, image settings, and voice preferences.

Chat

Chat controls

Choose the model, turn on web search or image tools, open canvas, talk by voice, and keep the current conversation moving.

Project

Project controls

Add a project when the work needs its own files, chats, memory, and a dedicated workspace instead of living in your global stream.

Capabilities

What chat includes.

Model choice, memory, tools, and output stay together in one workspace.

Customization

Your defaults live in Account.

Set custom instructions, nickname, occupation, more about you, tone controls, response font, and global files once, then let new chats start from there.

Adaptive memory

Memory is scoped, reviewable, and tied to the active workspace.

Global, project, and persona memory are kept in separate scopes. You can view, edit, delete, or turn off memory, and a badge appears in chat when automatic memory changes something.

Personas

A persona is a reusable set of instructions.

Create personas in Account and attach them to chats or projects. Their instructions and memory carry over when you switch models.

Projects

Projects keep chats, files, and memory in one working space.

Each project has its own chat list, files, icon, goal, and memory layer so long-running work stays in one place.

Canvas

Canvas adds a drafting surface beside chat.

Open a side-by-side document, edit files in place, review proposed hunks, and keep the conversation attached to the artifact you are producing.

Voice

Voice input and read-aloud stay inside the same chat flow.

Studio and above unlock voice input and read-aloud, while voice model, voice style, silence timing, and playback controls live in Account settings.

Tools

Search, image generation, data, voice, and canvas stay in one picker.

The tools button in the composer controls live web search, generated images, EIA plus BLS data, voice mode, and canvas without sending you to a different surface.

Import

You can start from history instead of rebuilding context from zero.

The migration tool parses ChatGPT exports, helps separate chats into files, and on Aurora and Pro can import up to 100 conversations into chat.

Providers

Models from multiple providers in one chat.

Choose models from OpenAI, Anthropic, Google, xAI, DeepSeek, Qwen, Moonshot, MiniMax, Z.ai, and our own Echo family in the same workspace.

OpenAI / ChatGPT logo

OpenAI / ChatGPT

GPT-4o, the GPT-5 and GPT-6 families, GPT OSS, and GPT audio models are available in chat.

Claude logo

Claude

Claude Sonnet and Claude Haiku models are available in chat.

Gemini logo

Gemini

Gemini 2.5, Gemini 3, Gemini 3.5, and Gemini 3.6 models are available in chat.

Grok logo

Grok

Grok 4.20, Grok 4.3, Grok 4.5, and Grok Build are available in chat.

DeepSeek logo

DeepSeek

DeepSeek chat and reasoning models are available in chat.

Qwen logo

Qwen

Qwen 3.6 Plus is available in chat.

Moonshot logo

Moonshot

Kimi models from Moonshot are available in chat.

MiniMax logo

MiniMax

MiniMax M2.5 and M3 are available in chat.

Z.ai logo

Z.ai

GLM 4.7 and the GLM 5 family are available in chat.

just4o.chat logo

just4o.chat

Echo mini, Echo, and Echo max are just4o.chat model profiles that run on third-party models.

Plan limits

Plan limits are shown up front.

just4o.chat shows when a feature is limited or unavailable on your plan.

Chat length20 / 250 / 500 / unlimited

Explorer gets 20 user messages per chat, Builder 250, Studio 500, and Aurora plus Pro remove the chat-length ceiling.

Web search0 / 5 / 10 / 25 / 50 per day

Explorer has no web search. Builder gets 5 per day, Studio 10, Aurora 25, and Pro 50.

VoiceGPT audio mini · Grok · ElevenLabs

Audio-native chat uses GPT audio models. Read-aloud uses GPT-4o mini TTS, Grok Voice, or ElevenLabs Flash v2.5. Available on Studio and above.

Open chat and start working.

The chat surface is where your model choice, memory, files, voice, and canvas meet.