All models
World modelsPrivate beta
Odyssey
Odyssey-2 Max
Odyssey's largest general world model, focused on real-time next-state simulation, physical accuracy, open-ended futures, and longer interactive rollouts.
Plain-English overview
What Odyssey-2 Max actually is
Odyssey-2 Max predicts how a scene evolves in response to actions instead of producing a predetermined clip. The announcement emphasizes physics, interaction, and long-horizon stability across robotics, games, simulation, and other interactive systems.
The current access path is a private beta for partners. That makes availability, contract terms, and integration support more important comparison criteria than a price that has not been published.
Good fit for
- Frontier robotics and simulation partnerships
- Interactive systems research
- Teams that can participate in a private beta
Category comparison
The facts that matter for world models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Price basisPublic API cost where available; research and private-beta models may not publish one.
- Not published
- Access stagePublic API, research experiment, partner onboarding, or private beta.
- Private beta
- What it createsThe kind of interactive environment or embodied experience produced.
- General-purpose next-state world simulation
- InteractionPublished frame rate, latency, or realtime behavior with its original basis.
- Realtime; exact fps not published
- Visual outputProvider-published resolution or output format where available.
- Not published
- API accessWhether developers can integrate the model today and under what access model.
- Partner/private beta
API and provider access
Where to get Odyssey-2 Max
Availability
Regions and access stage
Private beta for selected partners in robotics, gaming, simulation, defense, and interactive systems.
Regional and country availability is handled through partner onboarding rather than a public list.
Check live availabilityData and training
The route matters.
No public self-serve API data policy is attached to the private-beta announcement. Request retention, training-use, security, and residency terms during partner diligence.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Odyssey-2 Max FAQ
What is Odyssey-2 Max?
Odyssey's largest general world model, focused on real-time next-state simulation, physical accuracy, open-ended futures, and longer interactive rollouts. Odyssey-2 Max predicts how a scene evolves in response to actions instead of producing a predetermined clip. The announcement emphasizes physics, interaction, and long-horizon stability across robotics, games, simulation, and other interactive systems.
When was Odyssey-2 Max released?
Odyssey-2 Max was released on April 21, 2026 according to the cited provider materials.
Where can I access Odyssey-2 Max?
Private beta for selected partners in robotics, gaming, simulation, defense, and interactive systems. The access routes listed in this guide are Odyssey.
How much does Odyssey-2 Max cost?
Not published. Odyssey offers the model in private beta to selected partners; no public metered price is listed.
Where is Odyssey-2 Max available?
Private beta for selected partners in robotics, gaming, simulation, defense, and interactive systems. Regional and country availability is handled through partner onboarding rather than a public list.
Is my Odyssey-2 Max API data used for training?
No public self-serve API data policy is attached to the private-beta announcement. Request retention, training-use, security, and residency terms during partner diligence. The policy belongs to the provider route and account terms, so verify it again before production use.
Research trail
Sources for this guide
Keep comparing
More world models models
Google DeepMind · Research access
Genie 3
Google DeepMind's research world model for generating photorealistic, controllable environments that can be explored in real time from a text description.
Read guideWorld Labs · Stable
Marble 1.1 Plus
World Labs' public API model for turning text, images, panoramas, multi-view sets, or video into large explorable 3D worlds and spatial assets.
Read guideDecart · Preview
Oasis 3
Decart's action-conditioned world model for physical-AI training, generating synchronized, controllable simulation views in real time.
Read guide