{"id":"97239e0f-b2b4-4173-9758-a50f48732845","slug":"genie-3","name":"Genie 3","description":"Google DeepMind's world model that learns interactive action spaces from video without labeled data. Generates playable environments for robot training. Closed API only as of 2026. Builds on the Genie family of latent action models.","brainType":"world-model","isOpen":false,"maturityStage":"research","architecture":"Latent action model, learns compressed action space from video","reviewStatus":"reviewed","sources":[{"url":"https://deepmind.google/blog/genie-3-a-new-frontier-for-world-models/","date":"2025-08-05","title":"Genie 3: A new frontier for world models","sourceName":"Google DeepMind"},{"url":"https://blog.google/innovation-and-ai/models-and-research/google-deepmind/project-genie/","date":"2026-01-29","title":"Project Genie: Experimenting with infinite, interactive worlds","sourceName":"Google"},{"url":"https://deepmind.google/models/genie/","title":"Genie 3","sourceName":"Google DeepMind"}],"keyFacts":[{"label":"Genie 3 announcement (primary DeepMind)","value":"On Aug 5 2025 Google DeepMind announced Genie 3, a general-purpose world model. The post says a text prompt can generate dynamic worlds navigable in real time at 24 frames per second, retaining consistency for a few minutes at 720p, with visual memory extending as far back as one minute. It was announced as a limited research preview for a small cohort of academics and creators, not a public product (Google DeepMind)"},{"label":"Project Genie access (primary Google)","value":"On Jan 29 2026 Google said it was rolling out Project Genie, an experimental research prototype powered by Genie 3 (plus Nano Banana Pro and Gemini), to Google AI Ultra subscribers in the U.S. who are 18 or older, not including Google AI Ultra for Business. The post lists known limits including worlds that may not match real-world physics and generations limited to 60 seconds. Frame access and limits as Google-stated for the prototype, not the August research preview (Google)"},{"label":"General-purpose world model","value":"Google DeepMind describes Genie 3 as a general-purpose world model that generates photorealistic, interactive environments from text descriptions and lets users explore them in real time (Genie 3)."},{"label":"Interactive generation limits","value":"Google DeepMind's launch post says Genie 3 can generate dynamic worlds at 24 frames per second and 720p while retaining consistency for a few minutes, and was initially offered as a limited research preview (Genie 3 launch)."},{"label":"Genie interactive worlds","value":"Google DeepMind says Genie 3 generates interactive environments from text prompts that users can navigate in real time (Genie 3)."},{"label":"Genie real-time output","value":"Google DeepMind reports that Genie 3 can generate navigable worlds at 24 frames per second and 720p resolution for several minutes (Genie 3)."},{"label":"Genie embodied research","value":"Google DeepMind says Genie 3 worlds were used to test embodied-agent research and can support agent navigation goals (Genie 3)."},{"label":"Real-time interactive world model announcement (DeepMind)","value":"On August 5, 2025 Google DeepMind announced Genie 3 as a general-purpose world model that can generate interactive environments from text prompts, stating real-time navigation at 24 frames per second and 720p with consistency for a few minutes. Treat performance claims as company-stated (Google DeepMind)."},{"label":"Limited research preview and agent training framing (DeepMind)","value":"DeepMind stated Genie 3 was released as a limited research preview for a small cohort of academics and creators, and described using Genie 3 worlds with a recent SIMA agent for embodied goal-directed navigation research. Treat availability and agent results as company-stated (Google DeepMind)."}],"aliases":[],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-08-09T14:35:23.856Z","updatedAt":"2026-10-09T22:00:42.860Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/genie-3","url":"https://registry.deploy.report/brains/genie-3","name":"Genie 3","description":"Google DeepMind's world model that learns interactive action spaces from video without labeled data. Generates playable environments for robot training. Closed API only as of 2026. Builds on the Genie family of latent action models.","identifier":"97239e0f-b2b4-4173-9758-a50f48732845","applicationCategory":"world-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"research","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":3,"primary_source_types":[]}}}