# GenX Pro > Desktop AI agent with 105 models for chat, image, video, voice, and audio. Single App. Limitless capabilities. GenX Pro is a free desktop application (Mac and Windows) by GenX Pro LLC. Beast Agent gives you access to 105 AI models for chat (42 models), image generation (24 models), video generation (29 models), voice/TTS (6 models), and audio (4 models) — all from one app. AI usage options include Pay per use, Usage Plans and Owners Tier, managed in GenX Pro Console. - [Homepage](https://genx.pro/): Beast Agent — single app, 105 models, limitless capabilities ## Products - [GenX Pro for Business](https://genx.pro/business): Over 100 AI models for your team in one app, with owner-managed access, credit budgets, usage reports and shared team assets. No monthly subscription required. - [Beast Agent](https://genx.pro/#beast-agent): Research, analyze, create and complete multi-step tasks with AI models, files and connected tools - [Code Station](https://genx.pro/#code-station): Build and edit projects with Beast Agent, review changes and manage permissions - [App workflows](https://genx.pro/#workflows): Text Station, Voice Studio, Daily & Pod Shorts and Avatar Studio - [App models](https://genx.pro/#models): Featured AI models across Chat, Image, Video, Voice and Audio ## Creation guides Watch real films made with GenX Pro and follow the step-by-step process with copyable prompts. - [Not Really Here](https://genx.pro/create/not-really-here): A midnight arrival. Four words. A whole story in a moment. - [She Dropped Her Bag](https://genx.pro/create/she-dropped-her-bag): A city street. A chance encounter. The beginning of something. - [You Look Real](https://genx.pro/create/you-look-real): Two characters. A few words. Nothing quite as it seems. - [He Looked Up Too Late](https://genx.pro/create/he-looked-up-too-late): A dinner date told through the little things that go unnoticed. - [Boring Render](https://genx.pro/create/boring-render): A luxury commercial. An interrupted take. A very dramatic render. ## Features - [Pod Shorts](https://genx.pro/podshorts): Turn podcast episodes into viral short-form videos, ranked by hook score - [Daily Shorts](https://genx.pro/dailyshorts): 56 videos across 7 languages from a single script - [InteliScripts](https://genx.pro/inteliscripts): AI-generated viral scripts from any transcript - [Transcriptions](https://genx.pro/transcriptions): 92x realtime transcription engine - [Translations](https://genx.pro/translations): Document translation in 7 languages - [Voiceovers](https://genx.pro/voiceovers): Voice cloning + 1,000 pre-made voices - [MCP Server](https://genx.pro/mcp): 69 tools for AI agent automation via Model Context Protocol ## Developer Platform - [API Documentation](https://genx.pro/docs/api): REST API reference — authentication, endpoints, code examples, and pricing - [Model Catalog](https://genx.pro/models): AI models for text, image, video, and audio generation with per-model pricing - [MCP Server Docs](https://genx.pro/docs/mcp): Setup, configuration, and complete tool reference for the MCP Server - [Developer Portal](https://genx.sh): API keys, billing dashboard, usage analytics ## Public API Catalog 91 models from 12 providers. This public developer catalog differs from the App catalog above. ## AI Models (Text) - [Claude Haiku 5.5](https://genx.pro/models/claude-haiku-5-5): Anthropic — Fastest, lowest-cost Claude for high-volume work - [Claude Sonnet 5.5](https://genx.pro/models/claude-sonnet-5-5): Anthropic — Balanced agentic coding and knowledge work - [GPT-6.1 Sol](https://genx.pro/models/gpt-6.1-sol): OpenAI — Complex coding, agentic workflows, and professional work - [GPT-6 Sol](https://genx.pro/models/gpt-6-sol): OpenAI — Complex coding and agentic workflows - [GPT-6 Luna](https://genx.pro/models/gpt-6-luna): OpenAI — Efficient reasoning for focused, high-volume tasks - [Claude Opus 5.5](https://genx.pro/models/claude-opus-5-5): Anthropic — Long-running agentic coding and knowledge work - [Grok Build 0.1](https://genx.pro/models/grok-build-0.1): xAI — Agentic coding with 256K context - [Grok 4.7](https://genx.pro/models/grok-4.7): xAI — Coding, agentic tasks, and knowledge work - [Gemini 3.8 Flash](https://genx.pro/models/gemini-3.8-flash): Google — Long-running coding and agent workflows - [GPT-6 Astra](https://genx.pro/models/gpt-6-astra): OpenAI — Complex reasoning, coding, research, and document work - [Claude Fable 5.1](https://genx.pro/models/claude-fable-5-1): Anthropic — Demanding reasoning and long-horizon agentic work - [Grok 4.6](https://genx.pro/models/grok-4.6): xAI — xAI's frontier model for coding and agentic work - [Claude Opus 5](https://genx.pro/models/claude-opus-5): Anthropic — Flagship agentic coding with frontier reasoning - [Gemini 3.6 Flash](https://genx.pro/models/gemini-3.6-flash): Google — Latest fast multimodal model with audio and video input - [Gemini 3.5 Flash Lite](https://genx.pro/models/gemini-3.5-flash-lite): Google — Fast and affordable multimodal workhorse - [Grok 4.5](https://genx.pro/models/grok-4.5): xAI — xAI's flagship for code and agentic work - [GPT-5.6 Sol](https://genx.pro/models/gpt-5.6-sol): OpenAI — Frontier intelligence for complex professional work - [GPT-5.6 Terra](https://genx.pro/models/gpt-5.6-terra): OpenAI — Balanced intelligence and cost - [GPT-5.6 Luna](https://genx.pro/models/gpt-5.6-luna): OpenAI — Fast and affordable for high-volume workloads - [Claude Sonnet 5](https://genx.pro/models/claude-sonnet-5): Anthropic — Anthropic's best combination of speed and intelligence - [Claude Fable 5](https://genx.pro/models/claude-fable-5): Anthropic — Anthropic's most capable widely released model - [Claude Opus 4.8](https://genx.pro/models/claude-opus-4-8): Anthropic — Most capable agentic coding with effort control - [Grok 4.3](https://genx.pro/models/grok-4.3): xAI — xAI's flagship model with 1M token context - [GPT-5.5](https://genx.pro/models/gpt-5.5): OpenAI — Frontier intelligence for coding and professional work - [Claude Opus 4.7](https://genx.pro/models/claude-opus-4-7): Anthropic — Step-change agentic coding with 1M token context - [GPT-5.3 Codex](https://genx.pro/models/gpt-5.3-codex): OpenAI — Code-specialized model with 400K context - [GPT-5.4 Mini](https://genx.pro/models/gpt-5.4-mini): OpenAI — Fast, affordable GPT-5.4 variant - [GPT-5.4](https://genx.pro/models/gpt-5.4): OpenAI — Top-tier reasoning with up to 272K context - [GPT-5.4 Pro](https://genx.pro/models/gpt-5.4-pro): OpenAI — Enhanced GPT-5.4 with extended capabilities - [GPT-5](https://genx.pro/models/gpt-5): OpenAI — Capable general-purpose model with strong reasoning - [GPT-5 Mini](https://genx.pro/models/gpt-5-mini): OpenAI — Fast and affordable for everyday tasks - [GPT-5 Nano](https://genx.pro/models/gpt-5-nano): OpenAI — Most affordable model for simple, high-volume tasks - [Claude Opus 4.6](https://genx.pro/models/claude-opus-4-6): Anthropic — Most capable model with 1M token context - [Claude Sonnet 4.6](https://genx.pro/models/claude-sonnet-4-6): Anthropic — Balanced reasoning and coding at lower cost - [Claude Haiku 4.5](https://genx.pro/models/claude-haiku-4-5): Anthropic — Fastest model, optimized for speed and cost - [Gemini 3.1 Pro](https://genx.pro/models/gemini-3.1-pro): Google — Most capable multimodal model with image output - [Gemini 3 Flash](https://genx.pro/models/gemini-3-flash): Google — Fast multimodal model with audio input - [Gemini 3.1 Flash Lite](https://genx.pro/models/gemini-3.1-flash-lite): Google — Lightest model, optimized for speed and cost - [Grok 4.2 Multi-Agent](https://genx.pro/models/grok-4.2-multi-agent): xAI — Collaborative, parallel research tasks - [Grok 4.2 Reasoning](https://genx.pro/models/grok-4.2-reasoning): xAI — Deep reasoning for complex analytical tasks - [Grok 4.2](https://genx.pro/models/grok-4.2): xAI — Latest general-purpose model with broad knowledge - [GenX LM Pro v1 TL](https://genx.pro/models/genxlm-pro-v1-tl): GenX — Translation model for 9 languages ## AI Models (Image) - [GPT Image 2.5 Sunburst](https://genx.pro/models/gpt-image-2.5-sunburst): OpenAI — Image generation and precision editing - [Grok Imagine Image 2.0](https://genx.pro/models/grok-imagine-2): xAI — xAI's second-generation image model - [Recraft V4.1](https://genx.pro/models/recraft-v4.1): Recraft — High-aesthetic image generation - [Recraft V4.1 Pro](https://genx.pro/models/recraft-v4.1-pro): Recraft — Premium aesthetic generation at 2x resolution - [Recraft V4.1 Vector](https://genx.pro/models/recraft-v4.1-vector): Recraft — Editable SVG generation from text - [Recraft V4.1 Pro Vector](https://genx.pro/models/recraft-v4.1-pro-vector): Recraft — Premium SVG for complex compositions - [Recraft V4.1 Utility](https://genx.pro/models/recraft-v4.1-utility): Recraft — Flat lighting product mockups - [Recraft V4.1 Utility Pro](https://genx.pro/models/recraft-v4.1-utility-pro): Recraft — Production-grade flat-lighting mockups - [Recraft V4.1 Utility Vector](https://genx.pro/models/recraft-v4.1-utility-vector): Recraft — Structured SVG icon sets - [Recraft V4.1 Utility Pro Vector](https://genx.pro/models/recraft-v4.1-utility-pro-vector): Recraft — High-fidelity brand icon systems - [GPT Image 2](https://genx.pro/models/gpt-image-2): OpenAI — State-of-the-art image generation and editing - [Grok Imagine](https://genx.pro/models/grok-imagine): xAI — Creative and expressive image generation - [Nano Banana 2](https://genx.pro/models/nano-banana-2): Google — Creative and artistic image generation via Gemini - [Nano Banana Pro](https://genx.pro/models/nano-banana-pro): Google — Premium image generation via Gemini - [GenX LM Pro v1 IMG](https://genx.pro/models/genxlm-pro-v1-img): GenX — High-quality generation on dedicated GPUs - [GenX LM Pro v1 IMG Fast](https://genx.pro/models/genxlm-pro-v1-img-fast): GenX — Quick generation on dedicated GPUs ## AI Models (Video) - [Gemini Omni Flash](https://genx.pro/models/gemini-omni-flash): Google — Omni 1.1 video generation and conversational editing - [MiniMax H3 Max](https://genx.pro/models/minimax-h3-max): MiniMax — Prompt-faithful video with native audio - [MiniMax H3 Max I2V](https://genx.pro/models/minimax-h3-max-i2v): MiniMax — Animate a start frame or bridge two frames - [MiniMax H3 Max Reference](https://genx.pro/models/minimax-h3-max-r2v): MiniMax — Direct video from image, motion and audio references - [Seedance 2.5](https://genx.pro/models/seedance-2.5): ByteDance — Native 30-second single-shot video - [Seedance 2.5 I2V](https://genx.pro/models/seedance-2.5-i2v): ByteDance — Animate a still into 30 seconds - [Seedance 2.5 Reference](https://genx.pro/models/seedance-2.5-r2v): ByteDance — Up to 40 references, locked across a 30-second take - [Grok Imagine Video 1.5](https://genx.pro/models/grok-imagine-video-15): xAI — Reference-driven video with preset voices - [Seedance 2.0 Reference](https://genx.pro/models/seedance-2-r2v): ByteDance — Multi-reference video with up to 9 images, 3 videos, and 3 audio files - [Seedance 2.0](https://genx.pro/models/seedance-2): ByteDance — High-quality T2V with native audio and physically accurate motion - [Seedance 2.0 I2V](https://genx.pro/models/seedance-2-i2v): ByteDance — Animate images with end-frame control and native audio - [PixVerse v6](https://genx.pro/models/pixverse-v6): PixVerse — Cinematic text-to-video with style presets and flexible duration - [PixVerse v6 I2V](https://genx.pro/models/pixverse-v6-i2v): PixVerse — Animate images into cinematic video with style presets - [Kling Avatar 2.0 Pro](https://genx.pro/models/kling-avatar-v2-pro): Kling — Lip-synced talking avatars from image + audio - [Seedance v1 Fast I2V](https://genx.pro/models/seedance-v1-fast-i2v): ByteDance — Image-to-video via Fal.ai - [PixVerse v5.5 I2V](https://genx.pro/models/pixverse-v5.5-i2v): PixVerse — Stylized image-to-video via Fal.ai - [Kling v3 Pro I2V](https://genx.pro/models/kling-v3-pro-i2v): Kling — High-quality image-to-video via Fal.ai - [Kling v2.6 Pro I2V](https://genx.pro/models/kling-v2.6-pro-i2v): Kling — Image-to-video with audio via Fal.ai - [Kling v2.5 Turbo I2V](https://genx.pro/models/kling-v2.5-turbo-i2v): Kling — Fast image-to-video generation - [Veo 3.1](https://genx.pro/models/veo-3.1): Google — High-quality video from text via Gemini - [Veo 3.1 Fast](https://genx.pro/models/veo-3.1-fast): Google — Fast video generation at lower cost - [Grok Imagine Video](https://genx.pro/models/grok-imagine-video): xAI — Short video generation from text - [Kling v3 Pro](https://genx.pro/models/kling-v3-pro): Kling — High-quality text-to-video via Fal.ai - [Kling v2.6 Pro](https://genx.pro/models/kling-v2.6-pro): Kling — Reliable video generation via Fal.ai - [Kling v2.5 Turbo](https://genx.pro/models/kling-v2.5-turbo): Kling — Fast turbo video generation - [Seedance v1 Fast](https://genx.pro/models/seedance-v1-fast): ByteDance — Fast creative videos via Fal.ai - [PixVerse v5.5](https://genx.pro/models/pixverse-v5.5): PixVerse — Stylized video generation via Fal.ai ## AI Models (Voice) - [GenX LM Voice v1](https://genx.pro/models/genxlm-voice-v1): GenX Pro — Native voice cloning from reference audio - [Aura 2](https://genx.pro/models/aura-2): Deepgram — Natural, expressive text-to-speech - [Grok TTS](https://genx.pro/models/grok-tts): xAI — 169 expressive voices across 36 languages ## AI Models (Audio) - [Lyria 3 Clip Preview](https://genx.pro/models/lyria-3-clip-preview): Google — 30-second music clips from text or images - [Lyria 3 Pro Preview](https://genx.pro/models/lyria-3-pro-preview): Google — Full songs with lyrics, vocals, and structure ## AI Models (Transcription) - [GenX LM Pro v1 TR](https://genx.pro/models/genxlm-pro-v1-tr): GenX — Audio transcription on dedicated GPUs ## Company - GenX Pro LLC - [Releases](https://genx.pro/latest): Version history, changelogs, and download links - [FAQ](https://genx.pro/faq) - [Terms](https://genx.pro/terms) - [Privacy](https://genx.pro/privacy) - [Contact](https://genx.pro/contact)