
Work Here?
Meshy uses AI to generate 3D assets from text prompts or images in minutes. It provides Text-to-3D, Image-to-3D, AI texturing, and automated animation/rigging, with exports in FBX, GLB, and STL for Blender, Unity, and Unreal Engine. The platform combines modeling, texturing, and animation in a single workflow and offers a credit-based access model plus developer APIs and plugins. Its goal is to make 3D content creation faster and more accessible for game developers, artists, designers, hobbyists, and industries like gaming, XR, 3D printing, and architecture.
Industries
VR & AR
Consumer Software
AI & Machine Learning
Gaming
Company Size
51-200
Company Stage
Series B
Total Funding
$400M
Headquarters
San Jose, California
Founded
2021
See people who can refer or advise you
Help us improve and share your feedback! Did you find this helpful?
Total Funding
$400M
Above
Industry Average
Funded Over
1 Rounds
Industry standards
Health Insurance
Dental Insurance
Vision Insurance
401(k) Retirement Plan
401(k) Company Match
Stock Options
Unlimited Paid Time Off
Flexible Work Hours
Remote Work Options
Meshy details mora, a research architecture for ai-generated interactive worlds, and launches Meshy 7.1. Sep 21, 2026, 11:00 ET Publicly playable at mora.fun, Mora combines coding agents, 3D generation and real-time video; Meshy also introduces finer geometric detail with Meshy 7.1 SILICON VALLEY, Calif., Sept. 21, 2026 /CNW/ - Meshy, the AI-powered 3D generation platform, recently detailed Mora (Multimodal Open-world Real-time Architecture), its answer to one of the most ambitious goals in AI: generating complete worlds that people can explore, play and interact with in real time. Mora 1, an early demonstration available at mora.fun, features playable experiences ranging from spatial puzzles and multiplayer platforming to building, racing and sports, with switchable visual styles. Much of the industry has approached this goal by asking a single video model to simulate an entire world end to end - an approach that continues to struggle with consistent spaces and complex interaction. Mora is built on a different conviction: a world should be constructed, and only then rendered. The architecture assigns each part of world generation to the layer best equipped for it: coding agents write the logic and mechanics that make a world run; Meshy's 3D generation builds its spatial structure and assets; and a real-time video model turns that structure into final imagery and audio. The result is a foundation on which game rules hold, spaces persist, and visual quality rises with every generation of video models. Because the layers advance independently, progress anywhere in AI - stronger coding agents, richer 3D generation, faster video models - compounds inside Mora. For creators, the longer-term opportunity is to bring the elements of an interactive world into a more connected creative process. A change to how a game works could be developed alongside changes to how it looks, with agents helping to build and refine both. Because Mora separates these functions, advances in coding agents, 3D generation and video models can contribute to the architecture's development individually. Mora 1 is an early research demonstration focused on validating this architecture. Its public demos let visitors experience the approach through gameplay; a general-purpose world creation tool is a longer-term goal. Development of Mora 2 is underway as Meshy continues its research into richer AI-generated interactive experiences. Meshy 7.1: the first generative 3D model to reach 4096[3] geometric resolution Alongside its research into interactive worlds, Meshy continues to advance the 3D generation models at the core of its platform. On September 16, the company launched Meshy 7.1, the new version of its flagship image-to-3D model, now available to all registered users. Meshy 7.1 introduces two high-detail generation modes, Ultra 2K and Ultra 4K. At its Ultra 4K setting, Meshy 7.1 generates geometry at 4096[3] voxel resolution, with raw meshes reaching up to 80 million triangles before simplification. This makes Meshy 7.1 the first generative 3D model to reach 4096[3] geometric resolution. Fine features such as stitching, woven fabric and individual scales can be generated as part of the mesh itself. These geometric details matter in workflows such as 3D printing and digital sculpting, where surface structure must be carried by the model. In internal evaluations using Meshy's newly developed Detail Richness Benchmark, Meshy 7.1 ranked first among five tested image-to-3D models across all three evaluated rendering resolutions. The benchmark measures geometric surface detail, providing a focused assessment of this aspect of model quality. Methodology and results are available in Meshy's technical report, and the company plans to release the benchmark as a standalone tool. Ultra 2K and Ultra 4K modes, along with downloads of models generated by Meshy 7.1, require a paid subscription. Ultra 2K supports single-view and multi-view generation; Ultra 4K currently supports single-view generation. * What is Mora? Mora (Multimodal Open-world Real-time Architecture) is a research architecture developed by Meshy for creating AI-generated interactive worlds that people can explore, play and interact with in real time. Mora 1 is an early, publicly playable research demonstration, while a general-purpose world creation tool remains a longer-term goal. Development of Mora 2 is underway as Meshy continues its research into richer AI-generated interactive experiences. * How does Mora generate interactive worlds? Mora assigns different parts of world generation to specialized layers. Coding agents generate game logic and mechanics, Meshy's 3D generation provides assets and spatial structure, and a real-time video model generates the final imagery and audio. * What is the purpose of Mora's layered architecture? The architecture gives game rules and spatial relationships an explicit foundation in code and 3D graphics, allowing the video model to focus on visual presentation. The approach is designed to address challenges in maintaining consistent spaces and supporting complex interactions. * Where is Mora 1 available? Mora 1's playable research demonstrations are available at mora.fun. Current experiences include spatial puzzles, multiplayer platforming, building, racing and sports, with switchable visual styles. * What is Ultra 4K? Ultra 4K is one of two high-detail generation modes introduced in Meshy 7.1, alongside Ultra 2K. It generates geometry at 4096[3] voxel resolution, the highest setting available, so fine features such as stitching, woven fabric and individual scales are built into the mesh itself rather than painted on as textures. Ultra 4K currently supports single-view generation and requires a paid subscription. About Meshy Meshy builds foundation models for AI-powered 3D generation, helping people turn text and images into 3D assets for games, film, design and 3D printing. Founded by Ethan Hu, who holds a Ph.D. from MIT, Meshy serves more than 12 million registered users worldwide. In July 2026, the company announced nearly $400 million in Series B funding at a $1.5 billion valuation. Learn more at meshy.ai. SOURCE Meshy Runbo Li, Brand & Communications, [email protected]
Meshy has introduced Mora, a research architecture for AI-generated interactive worlds, alongside the launch of Meshy 7.1. Available at mora.fun, Mora 1 features playable experiences including puzzles, platforming, building, racing and sports with switchable visual styles. Mora uses a layered approach: coding agents handle game logic, Meshy's 3D generation creates spatial structure and assets, whilst a real-time video model produces final imagery and audio. This contrasts with single video models that struggle with consistent spaces and complex interaction. Meshy 7.1 introduces Ultra 2K and Ultra 4K generation modes. At Ultra 4K setting, the model generates geometry at 4096³ voxel resolution, reaching up to 80 million triangles — the first generative 3D model to achieve this resolution. Fine details like stitching and woven fabric are built into meshes rather than painted as textures.
Meshy, an AI 3D generation company, has appointed Dr. Xin Tong as Chief Scientist. Dr. Tong, who spent 25 years at Microsoft Research Asia, will lead the company's long-term research strategy, focusing on next-generation 3D foundation models and multimodal world systems. Dr. Tong has published over 190 papers and his work has been cited more than 21,000 times. His research includes O-CNN, an octree-based architecture for processing high-resolution 3D shapes, and recent projects like TRELLIS and MoGe. The appointment marks Meshy's expansion from creating individual 3D assets to building systems that can understand and run complete digital worlds. Meshy raised nearly $400 million in July 2026 at a $1.5 billion valuation and serves over 12 million registered users.
Big news: The Meshy AI 3D Model Generator is now live on KishMake. KishMake is thrilled to announce its partnership with Meshy! You can now choose the best AI engine for your specific 3D printing needs directly within KishMake. August 21, 2026 KishMake now officially integrates the Meshy AI 3D model generator, allowing you to seamlessly design and generate high-quality, print-ready 3D models using Meshy's advanced engine. This exciting partnership gives creators the freedom to choose the perfect AI model for their specific 3D printing projects directly within its platform. What is the new Meshy AI 3D Model Generator integration? Its new Meshy AI 3D model generator integration is a platform update bringing Meshy's powerful text-to-3D capabilities directly into KishMake. You can now seamlessly toggle between top-tier AI engines to ensure your generated models have the exact style, optimal geometry, and intricate details you need for flawless 3D printing. For months, its community has been asking for more variety in how geometries are generated. Different prompts require different algorithmic approaches. By bringing Meshy into the fold, KishMake is expanding your creative toolkit. Whether you are generating a custom slime fidget, a stylized tabletop miniature, or a decorative planter, having access to multiple text-to-3D engines drastically increases your chances of getting a perfect result on the first try. Why are KishMake thrilled to partner with Meshy? KishMake is incredibly excited about this partnership because it completely removes technical barriers for its community of makers. Integrating this top-tier generative technology directly into its ecosystem means you no longer need complex software to achieve stunning, print-ready results. It empowers everyone to create and sell better physical products. Meshy has proven itself to be one of the most innovative players in the generative 3D space. As highlighted by industry experts at All3DP, generative AI tools are fundamentally transforming how creators conceptualize and fabricate real-world items. Meshy's ability to interpret complex natural language prompts and output highly coherent, structurally sound meshes is remarkable. By baking their API right into its interface, print shops, hobbyists, and digital sculptors get the best of both worlds. You get the phenomenal AI processing power of Meshy combined with the automated print-preparation and user-friendly ecosystem of KishMake. Truly, it is The Easiest Way to Design for 3D Printing Today - Powered by AI. Meshy Integration Specs Cost Standard KishMake Credits Best for Detailed organic shapes, character models, and complex surface textures. Tripo or Meshy: which engine should I choose? Choosing the right AI engine depends entirely on your specific project requirements. While Tripo often excels at generating rapid, stylized geometric concepts, Meshy stands out for highly detailed organic shapes and intricate textures. Switching between them allows you to find the absolute perfect geometry for your 3D printing setup. Having choices is empowering, but it can also be a bit overwhelming. The beauty of its new update is that you don't have to lock yourself into a single workflow. You can experiment with a prompt in Tripo, and if the result isn't exactly what you envisioned for your FDM or Resin printer, you can immediately run the exact same prompt through Meshy. If you are planning to monetize your creations and want a comprehensive breakdown of when to use which tool, KishMake highly recommend reading its complete comparison guide: Meshy vs Tripo: Which is the Best AI 3D Model Generator for 3D Printing? It dives deep into edge cases, topology differences, and slicer compatibility. Quick comparison overview. | Feature | Meshy Engine | Tripo Engine | | Organic Details | Exceptional for fluid, natural curves | Good, but leans stylized | | Hard Surface | Strong, but sometimes over-smooths edges | Excellent for sharp geometric angles | | Speed | Fast, cloud-processed generation | Ultra-fast rapid ideation | How to generate Meshy models in KishMake. KishMake has designed the interface to be as intuitive as possible. You don't need a separate subscription to Meshy, nor do you need to learn a new dashboard. Everything happens right where you already work. Unlocking new possibilities for creators. The addition of the Meshy AI 3D model generator is just another step in its mission to democratize 3D design. KishMake know that many of its users run small businesses, Etsy shops, or local craft stalls. By providing you with the highest quality generative tools available on the market, KishMake is giving you a competitive edge. KishMake cannot wait to see what you build with Meshy. Whether you are creating intricate tabletop terrain, custom functional home decor, or unique personalized gifts, the power is now entirely in your hands. Head over to your KishMake dashboard today and take the Meshy engine for a spin! Frequently asked questions. Do I need a separate Meshy account to use this feature? No, you do not need a separate account to use the new features. The Meshy AI 3D model generator is fully integrated directly into the KishMake platform. Simply log into your existing KishMake workspace, select the Meshy engine from the dropdown menu, and start generating your printable models instantly. Does generating Meshy models cost extra in KishMake? Using the Meshy engine draws from your standard KishMake credit balance. There are no hidden fees or separate subscription requirements for accessing these advanced generation tools. You can seamlessly switch between different AI models based on what works best for your specific 3D printing budget and project needs. Are the Meshy 3D models ready for 3D printing? Yes, models generated through its platform are optimized for 3D printing. While some complex organic shapes might require minor slicer supports, the Meshy integration ensures that the initial geometry is solid and watertight. You can export these designs directly as STL or OBJ files to your favorite slicing software.
Meshy 7 improves image-to-3d accuracy with new Geometry Alignment technology. Meshy has released a new version of their AI-powered image-to-3D model service. They released Meshy 7, an upgrade over the previous Meshy 6. What's different? It seems they have focused on something they call "3D geometry alignment". This is the fancy term for: "did it actually match the input image?" That is indeed a problem with many of today's image-to-3D services: a very nice image is turned into a rough and poorly representative 3D model. That is what's powering the AI slop problem in many online 3D model repositories. I've written about this previously, where the 3D model is nowhere near the same as the image presented. It looks like Meshy wants to eliminate that problem with Meshy 7. I'm glad they're doing this, because everyone should be able to generate accurate 3D models from images. That really hasn't been the case with most tools, unless you happen to be lucky. How did they do this? Their first step was to invent a method of measuring accuracy. They developed their "first" 3D Geometry Alignment Benchmark. This is a test that measures three important factors: * Overall Proportion: measures whether major elements of the generated model occupy the same region of 3D space. This looks at the model as a whole. * Spatial Distribution: measures the fine details, looking at how far off each generated point is from a reference model. * Surface Details: measures the quality of the surface for missing or extra geometry. Armed with a measurement tool, they can then do some measuring. They benchmarked the new Meshy 7 against four competitors, suspiciously named T1, H1, R1, and H2. (By mere coincidence, Meshy's main competitors happen to be Tribo, Hi3D, Rodin, and Hunyuan.) Here are the results of their testing: Meshy 7 comes out quite well on the testing, although the measurements in each category are really fairly close. I do notice that all of them are pretty poor on surface detail, which aligns with my experiences. Interestingly, they didn't list the results for Meshy 6. Meshy does state that there are further measurements that could be taken, including texture alignment. That's the surface colouring that is also generated during the process, and is separate from the geometry. But you have to have geometry before you can have a texture, and for 3D print purposes, the geometry matters a lot more. What did they change in Meshy 7 to improve the results? They say they improved the image encoder to use higher resolutions, and rebuilt the training data with examples that have tighter alignment. They also now use alignment as their key metric when iterating through training loops. For Meshy users, this just makes things better; for others, it makes the choice between Meshy and its competitors a bit more complicated. Regardless, I see this as a continuation of the refinement of AI 3D technology. With each new release, the results are getting better and at some point will become much more usable than they are today. By kerry Stevenson. Kerry Stevenson, aka "General Fabb" has written over 8,000 stories on 3D printing at Fabbaloo since he launched the venture in 2007, with an intention to promote and grow the incredible technology of 3D printing across the world. So far, it seems to be working!
Find jobs on Simplify and start your career today
Industries
VR & AR
Consumer Software
AI & Machine Learning
Gaming
Company Size
51-200
Company Stage
Series B
Total Funding
$400M
Headquarters
San Jose, California
Founded
2021
Find jobs on Simplify and start your career today