Models
All ChatQT models
From GPT and Claude to Sora, Nano Banana and ElevenLabs — all in one panel. One shared credit; pick the right model for each job.
Major providers
See the dedicated page for each brand, or start directly in the app.
Guide
Models by task type
For each capability you get several models from different makers — switch between them in the app and try the best option for each project.
Chat & reasoning
Access ChatGPT, Claude, Gemini, Grok, Kimi, DeepSeek (V3.2 and V4), GLM 5 and QT models (such as R1 and Llama 4 Maverick) from a single window. Converse in your language, get output in any language, and your history is saved.
Image Generation
Use Nano Banana Pro and Nano Banana, GPT Image 1.5, FLUX.2 Pro, Imagen 4 and Ultra, Grok Image, Seedream and SD Ultra — from idea to professional output.
Nano BananaGoogle's lighter version (Gemini 2.5 Flash Image) — good for fast iteration and lower cost.
Nano Banana ProGoogle's pro version (Gemini 3 Pro Image) — higher quality, text on images and better scene control.
GPT Image 1.5OpenAI's image model — multi-style, high detail and good for text inside images.
FLUX.2 ProBlack Forest Labs — photorealism and precise, professional-grade editing.
Imagen 4Google's flagship image model — balanced quality, text on images and varied styles.
Imagen 4 UltraThe most detail in the Imagen 4 family — for demanding visual finishing.
Grok Image ProxAI — the advanced version of Grok image generation.
Grok ImagexAI — fast text-to-image generation.
SD UltraStability AI — outstanding quality and fine detail.
Video Generation
Create professional clips with Sora 2, Veo 3.1 and Veo 3.1 Fast, Grok Video, Kling 2.6 Pro, Minimax, Wan 2.2 and Hunyuan Video, and compare each model's output side by side.
Sora 2OpenAI — short video with cinematic quality and synced audio.
Veo 3.1Google — high quality and natural motion; great for ads and teasers.
Veo 3.1 FastGoogle — a faster version for more iteration and testing.
Grok VideoxAI — text or image to video with a distinct style.
Kling 2.6 ProKuaishou — motion control and longer scenes.
MinimaxMinimax — 720p video, Director and Live.
Wan 2.2Alibaba — high visual-quality video from text.
WaWan 2.1 ProAlibaba — 1080p, 30fps up to about 6 seconds.
Hunyuan VideoTencent — T2V via AI Model.
Text to Speech
Create natural-sounding voice with ElevenLabs (Multilingual v2, Turbo v2.5), OpenAI TTS 1 and TTS 1 HD, Speechify Simba and Google TTS Studio.
ElevenLabsMultilingual v2, Turbo v2.5, v1OpenAI TTSTTS 1 and TTS 1 HD
SpeechifySimba English, Multilingual, TurboGeminiGoogle TTS Studio
Speech to Text
Transcribe audio and video files with Whisper (99 languages) and QTstt, optimized for Persian.
WhisperOpenAI — high-accuracy multilingual transcription for podcasts, meetings and subtitles.
QTsttChatQT's own model — focused on everyday Persian and local idioms.
Noise Removal
Clean up recorded audio with ElevenLabs Voice Isolator — great for podcasts, calls and video.
ElevenLabs Voice IsolatorSeparate human voice from ambient noise, fans, wind and background music.All models, one credit
Top-up packages differ only in the amount of credit; all users have access to every capability and available model. Package details and usage rates are on the pricing page.
View pricingFAQ