# AI models for game development Every video, image, 3D, audio and motion model in Summer, with game uses and MCP access. Cost depends on the models you choose. Your dashboard shows spend as it happens. ## Video - [Gemini Omni Flash](https://www.summerengine.com/models/gemini-omni-flash) by Google: Fast video with synchronized audio from text, a still image, references, or a motion clip. - [Veo 3.1 Fast](https://www.summerengine.com/models/veo-3-1-fast) by Google: The faster, cheaper Veo tier for drafting shots with native audio. - [Veo 3.1](https://www.summerengine.com/models/veo-3-1) by Google: Google's premium Veo tier for coherent shots with native audio. - [Seedance 2.0 Fast](https://www.summerengine.com/models/seedance-2-0-fast) by ByteDance: Fast multimodal video with audio and clips up to 15 seconds. - [Seedance 2.5](https://www.summerengine.com/models/seedance-2-5) by ByteDance: Cinematic long takes with sound, from text, a still image or a set of references. - [Seedance 2.0](https://www.summerengine.com/models/seedance-2-0) by ByteDance: The higher-quality Seedance tier for audio-backed clips up to 15 seconds. - [Kling 3.0](https://www.summerengine.com/models/kling-3-0) by Kuaishou: Fluid motion, native audio, and motion transfer from a reference clip onto your character. - [MiniMax H3 Max](https://www.summerengine.com/models/minimax-h3-max) by MiniMax: Ranked first for image to video, with sharp motion up to 15 seconds. - [Wan 3.0](https://www.summerengine.com/models/wan-3-0) by Alibaba: Alibaba's Wan 3.0, smooth motion and native audio from a prompt, a frame or references. - [HappyHorse 1.1](https://www.summerengine.com/models/happy-horse-1-1) by Alibaba: Native audio with multilingual lip sync, written straight into the prompt. - [Veo 3.1 Lite](https://www.summerengine.com/models/veo-3-1-lite) by Google: The lowest-cost Veo tier, 720p clips with native audio. - [Grok Imagine Video 1.5](https://www.summerengine.com/models/grok-imagine-video-1-5) by xAI: xAI's video model with sound, from a prompt, a still or references. - [Vidu Q3 Pro](https://www.summerengine.com/models/vidu-q3-pro) by Vidu: Vidu's Q3 Pro model, clips with audio up to 16 seconds. - [PixVerse V6](https://www.summerengine.com/models/pixverse-v6) by PixVerse: Fast, low-cost clips with sound. - [LTX-2.5 Pro](https://www.summerengine.com/models/ltx-2-5-pro) by Lightricks: Lightricks' open-source audio and video model, sound and picture in one pass. - [Luma Ray 3.2](https://www.summerengine.com/models/luma-ray-3-2) by Luma: Luma's cinematic video model, rich camera work and seamless loops. ## Image - [Grok Imagine 2](https://www.summerengine.com/models/grok-imagine-2) by xAI: Concept images from xAI's Grok Imagine 2.0 at standard 1K output. - [Nano Banana 2 Lite](https://www.summerengine.com/models/nano-banana-2-lite) by Google: Fast 1K image generation and reference editing for clean game-asset references. - [Seedream 5.0 Pro](https://www.summerengine.com/models/seedream-5-0-pro) by ByteDance: Strong prompt understanding, multilingual text, and structured layouts. - [Nano Banana Lite](https://www.summerengine.com/models/nano-banana-lite) by Google: Fast 1K generation and reference editing for asset iteration. - [Grok Imagine](https://www.summerengine.com/models/grok-imagine) by xAI: Fast, sharp concept art and textures at a low price per image. - [GPT Image 2.5](https://www.summerengine.com/models/gpt-image-2-5) by OpenAI: OpenAI's top-ranked image model, with real light, exact text and faithful edits. - [GPT Image 2](https://www.summerengine.com/models/gpt-image-2) by OpenAI: Precise text, UI, and structured image generation from OpenAI. - [Muse Image](https://www.summerengine.com/models/muse-image) by Meta: Fast, near-frontier images and precise edits at the lowest price. - [Gemini 2.5 Flash Image](https://www.summerengine.com/models/gemini-2-5-flash-image) by Google: Fast general-purpose image generation and editing from Google. - [FLUX.2](https://www.summerengine.com/models/flux-2) by Black Forest Labs: The model behind Summer Pixel: crisp, consistent pixel art sprites. ## 3D - [Hunyuan 3D 3.1 Pro](https://www.summerengine.com/models/hunyuan-3d-3-1-pro) by Tencent: High-quality geometry and textures from Tencent's Hunyuan 3D v3.1. - [Hunyuan 3D 3.1 Rapid](https://www.summerengine.com/models/hunyuan-3d-3-1-rapid) by Tencent: Fast, lower-cost 3D drafts for shape checks. - [Rodin 2.5](https://www.summerengine.com/models/rodin-2-5) by Hyper3D: Production-focused geometry, PBR materials, and clean topology from up to five references. - [Meshy 6](https://www.summerengine.com/models/meshy-6) by Meshy: Meshy 3D with the rigging and animation path for characters. - [Tripo H3.1](https://www.summerengine.com/models/tripo-h3-1) by Tripo: Detailed geometry, PBR, quad output, and multi-view generation. - [Trellis 2](https://www.summerengine.com/models/trellis-2) by Microsoft: Image to 3D mesh through the Summer MCP, from any engine. - [Meshy 7.1](https://www.summerengine.com/models/meshy-7-1) by Meshy: Meshy's newest model, with quad or triangle meshes and one-step rigging for characters. - [Tripo P2](https://www.summerengine.com/models/tripo-p2) by Tripo: The first model to build native quad meshes, with texture tiers up to extreme. - [Hi3D V3.0](https://www.summerengine.com/models/hi3d-v3-0) by Hitem3D: The finest geometry detail, built at 2048 cubed voxel resolution. - [Rodin 2.5 Fast](https://www.summerengine.com/models/rodin-2-5-fast) by Hyper3D: Hyper3D's fast tier: light meshes up to 20K faces for quick drafts. ## Audio - [Eleven v3](https://www.summerengine.com/models/eleven-v3) by ElevenLabs: ElevenLabs' most emotionally rich speech model, with multi-speaker dialogue. - [Eleven Multilingual v2](https://www.summerengine.com/models/eleven-multilingual-v2) by ElevenLabs: Stable, lifelike speech for longer narration in many languages. - [Eleven Flash v2.5](https://www.summerengine.com/models/eleven-flash-v2-5) by ElevenLabs: Low-latency speech for fast iteration. - [ElevenLabs Text to Sound v2](https://www.summerengine.com/models/eleven-text-to-sound-v2) by ElevenLabs: Sound effects, loops, and ambience from a prompt. - [Sonilo SFX 1.1](https://www.summerengine.com/models/sonilo-sfx-1-1) by Sonilo: Detailed sound effects and ambience from a prompt. - [Stable Audio 3 SFX](https://www.summerengine.com/models/stable-audio-3-sfx) by Stability AI: Fast sound effects, strong on quick movement. - [Eleven Music v2](https://www.summerengine.com/models/eleven-music-v2) by ElevenLabs: Music with stronger vocals, arrangement, and long-form structure. - [Eleven Music v1](https://www.summerengine.com/models/eleven-music-v1) by ElevenLabs: Studio-grade music from a prompt or a composition plan. - [Gemini 3.8 Flash TTS](https://www.summerengine.com/models/gemini-3-8-flash-tts) by Google: Google's newest speech model, directed in plain words. - [Gemini 3.8 Flash Lite TTS](https://www.summerengine.com/models/gemini-3-8-flash-lite-tts) by Google: The lighter Gemini 3.8 speech model, for more lines for less. - [MiniMax Speech 2.8 HD](https://www.summerengine.com/models/minimax-speech-2-8-hd) by MiniMax: Studio-grade speech with emotion, pitch and speed controls. - [xAI TTS](https://www.summerengine.com/models/xai-tts) by xAI: Grok's expressive voices, with laugh, sigh and pause tags. - [Qwen Audio 3.0 TTS](https://www.summerengine.com/models/qwen-audio-3-tts) by Alibaba: Alibaba's speech model with 45 character voices. - [Inworld TTS-1.5 Max](https://www.summerengine.com/models/inworld-tts-1-5-max) by Inworld: Game-ready character voices from Inworld, at the lowest price here. - [ElevenLabs Scribe v2](https://www.summerengine.com/models/elevenlabs-scribe-v2) by ElevenLabs: Transcripts with word timings and speaker labels. - [Whisper Large v3](https://www.summerengine.com/models/whisper-large-v3) by OpenAI: OpenAI's Whisper in 99 languages, or translated to English. ## Motion - [Hunyuan Motion](https://www.summerengine.com/models/hunyuan-motion) by Tencent: Custom skeletal animation for a rigged character from a text description. - [Meshy animation library](https://www.summerengine.com/models/meshy-animation-library) by Meshy: Prebuilt walk, run, jump, attack and idle clips for a rigged character, by name. --- ## Machine-readable resources - Site index for agents: https://www.summerengine.com/llms.txt - Full inlined content: https://www.summerengine.com/llms-full.txt - Porting catalog: https://www.summerengine.com/llms-porting.txt - Structured catalog: https://www.summerengine.com/agent-catalog.json - Sitemap: https://www.summerengine.com/sitemap.xml - Developer resources: https://www.summerengine.com/docs