Question 1

What is SmaxAI and what makes it unique?

Accepted Answer

SmaxAI brings multiple AI models into one service, with chat, task-aware model routing, image and video creation, audio tools, writing, graphic design, and specialist agents. Feature availability depends on the current model and service configuration.

Question 2

How does SmaxAI compare to using ChatGPT, Claude, or Gemini separately?

Accepted Answer

SmaxAI lets you use different AI models from one interface, with Auto routing available for supported tasks. Model access, pricing, and provider availability can change; compare the current plan details with the services you use before deciding what it replaces.

Question 3

What are Pragg Air and Pragg Max routing profiles?

Accepted Answer

Pragg Air is designed for quick responses and task routing. Pragg Max is intended for deeper reasoning and more complex problem-solving. Actual speed and quality depend on the selected route and provider.

Question 4

How does the intelligent Auto Routing engine choose the best model?

Accepted Answer

Auto routing uses the request type and the routing configuration available at the time to choose a supported model or tool. It may select a different route when providers are unavailable; it does not guarantee the fastest or best result for every prompt.

Question 5

Can I use SmaxAI on mobile devices (iOS / Android)?

Accepted Answer

You can access SmaxAI through a supported mobile browser. Layout and available features can vary by device, browser, and model or studio.

Question 6

Is there a guest or trial mode available?

Accepted Answer

Guest access at /app allows a limited number of chat messages without an account. Sign in to save conversations and use account-based features. Media generation and some other features require an account.

Question 7

How do I switch between dark mode, light mode, and system theme?

Accepted Answer

Open Settings > Appearance to choose a light, dark, or system theme, where that setting is available.

Question 8

Which flagship reasoning and foundation models are supported?

Accepted Answer

Open the model selector to see the models currently available to your account. Names, capabilities, and availability can change when providers update or integrations are adjusted.

Question 9

How does SmaxAI maintain zero downtime and fast inference?

Accepted Answer

SmaxAI may retry or use configured fallback providers when a model is unavailable. Provider outages, rate limits, and network problems can still interrupt a request, so uninterrupted service is not guaranteed.

Question 10

What is DeepSeek R1 and when should I use it?

Accepted Answer

DeepSeek R1 is an open-weights reasoning model that outputs visible chain-of-thought tokens. It excels at competitive programming, algorithmic puzzles, formal mathematical derivation, and deep debugging.

Question 11

How does web search work inside chat sessions?

Accepted Answer

When research or live search is triggered, SmaxAI queries real-time web indexes, synthesizes multiple reputable sources, and provides inline verified citations.

Question 12

Can SmaxAI process file attachments and documents (PDF, CSV, TXT)?

Accepted Answer

Yes. You can attach PDF research papers, CSV datasets, Python scripts, or plain text files. SmaxAI parses the content and injects it into context for analysis, summarization, or data extraction.

Question 13

Does SmaxAI support multimodal image analysis?

Accepted Answer

Yes. Uploading screenshots, diagrams, UI wireframes, or artwork allows models like Gemini and GPT-4o to inspect visuals, detect bugs, or describe components with high accuracy.

Question 14

How are context windows and token lengths handled?

Accepted Answer

Context windows adapt dynamically according to the active model, ranging from 128k to 1M tokens. Long chats are intelligently summarized to keep latency minimal and prevent context overflow.

Question 15

What is the Unified Creative Studio?

Accepted Answer

Unified Creative Studio (/app/creative and /app/studio) brings Image Studio, Video Studio, and Audio Studio into a single cohesive workspace inspired by Leonardo AI, featuring full-screen model selection, reference image inputs, and a generation inspector.

Question 16

How do I generate AI videos using Google Veo?

Accepted Answer

In the Video Studio tab, enter a motion prompt or attach a starting reference image. Veo synthesizes fluid motion, cinematic lighting, and realistic camera physics at 720p or 1080p.

Question 17

What is the maximum duration for video generation?

Accepted Answer

Videos can be configured for up to 12 seconds max. Durations include 4s, 6s, 8s, 10s, and 12s, with automated cloud scaling for stable output.

Question 18

How do I use reference images inside the prompt composer?

Accepted Answer

The prompt input card contains an integrated reference image manager. You can attach up to 4 reference images via file picker, drag-and-drop, or direct Ctrl+V clipboard paste.

Question 19

Can I paste images using Ctrl+V or drag-and-drop into Creative Studio?

Accepted Answer

Yes! Simply copy any image to your clipboard and hit Ctrl+V while focused anywhere on the composer, or drag and drop image files directly onto the input card.

Question 20

How does Audio Studio generate music and songs with vocals?

Accepted Answer

Audio Studio uses Google Lyria and Suno music models to generate complete instrumental or vocal compositions across Folk, Classical, Lo-fi, Cinematic, and Synthwave genres from descriptive prompts or lyrics.

Question 21

Which image generation models are available?

Accepted Answer

The Model Library includes Google Imagen 3, Black Forest Labs Flux (Pro, Dev, Schnell), Stable Diffusion 3.5, and specialized photorealistic and stylized diffusion checkpoints.

Question 22

What are the aspect ratio and resolution options?

Accepted Answer

Supported ratios include Square (1:1), Widescreen (16:9), Vertical/Reel (9:16), Portrait (3:4), Landscape (4:3), and an intelligent [ Auto ] mode that infers the best ratio from your prompt keywords.

Question 23

What is the Canva-grade Graphic Canvas Studio?

Accepted Answer

Graphic Canvas Studio (/app/design) is a visual canvas featuring vector shape layers, 24+ Google fonts, tables, hand-drawn doodles, AI inpainting, background removal, and export to PNG/SVG.

Question 24

What features does Document Writer Studio include?

Accepted Answer

Document Writer Studio (/app/writer) provides A4/Letter page setups, formatting, subscript/superscript, formal AI letter/application drafting, and instant print-to-PDF generation.

Question 25

How do I use the 3D Spatial CAD Studio?

Accepted Answer

3D Spatial CAD (/app/spatial) is an interactive WebGL environment where you can model 3D primitives, apply metallic/roughness textures, manipulate camera perspectives, and generate text-to-3D models.

Question 26

Can I export documents directly to PDF or print them?

Accepted Answer

Yes. Document Writer Studio includes a direct 'Print to PDF' action with correct A4 margins, headers, and page breaks.

Question 27

How do vector layers and Google Fonts work in Canvas?

Accepted Answer

Every canvas element is a discrete layer that can be grouped, reordered, styled with dropshadows/gradients, and formatted using curated typography.

Question 28

Does 3D Spatial CAD support text-to-3D or image-to-3D?

Accepted Answer

Yes, experimental 3D geometry synthesis allows generating initial mesh objects from text descriptions or reference silhouettes.

Question 29

Are my canvas designs and documents saved automatically?

Accepted Answer

Yes. All projects are stored under your personal account database and accessible anytime from the Projects dashboard.

Question 30

What is Aura Live Duplex Voice?

Accepted Answer

Aura Live is SmaxAI's real-time conversational voice assistant capable of bidirectional duplex speech, allowing natural voice conversations with rapid audio responses.

How can we assist you today?

Frequently Asked Questions

Still need help?