Decart
Decart is an AI research lab and API platform building real-time world models — foundation models that generate and transform video frame-by-frame as they are watched. Its Decart API Platform (platform.decart.ai) exposes the Lucy family of realtime and batch video/image models plus the Oasis promptable world model through three surfaces: a Realtime API that edits a live WebRTC camera or video stream with text prompts and reference images, a Queue API that submits asynchronous video jobs and polls them to completion, and a Process API for synchronous image editing. The platform ships first-party JavaScript, Python, Swift and Android SDKs, ephemeral client tokens for browser and mobile apps, a Files API for reusable reference images, and a gRPC action-to-video session protocol for Oasis 3 Preview. Pricing is pay-as-you-go and metered per generated second (video and realtime) or per generation (images).
Decart publishes 9 APIs on the APIs.io network, including Realtime API, Client API, Files API, and 6 more. Tagged areas include Artificial Intelligence, Machine-Learning, Video, Video Generation, and Video Editing.
Decart’s developer surface includes documentation, API reference, getting-started guide, quickstart, engineering blog, support, pricing, and 36 more developer resources.
Kin Score
APIs 11
Individual APIs this provider publishes, each with its own machine-readable definition.
Decart Realtime API
The realtime video transformation surface. A client opens a WebRTC session (LiveKit-managed transport) against a Lucy realtime model and streams camera or video frames in; the m...
Decart Oasis Action-to-Video (gRPC)
A gRPC session protocol for Oasis 3 Preview, Decart's promptable real-time world model. A client initializes a session, sets a scene with a text prompt, then loops Infer calls t...
Decart Documentation MCP Server
A hosted, unauthenticated Model Context Protocol server at docs.platform.decart.ai/mcp that exposes the Decart API Platform documentation to agents. Three tools: full-text searc...
Decart Client API
The Client API from Decart — 1 operation(s) for client.
Decart Files API
The Files API from Decart — 2 operation(s) for files.
Decart Generate API
The Generate API from Decart — 4 operation(s) for generate.
Decart Jobs API
The Jobs API from Decart — 43 operation(s) for jobs.
Decart Models API
The Models API from Decart — 1 operation(s) for models.
Decart Realtime API
The Realtime API from Decart — 1 operation(s) for realtime.
Decart Verify API
The Verify API from Decart — 1 operation(s) for verify.
Decart Watch Stream API
The Watch Stream API from Decart — 1 operation(s) for watch stream.
Scroll for all 11
Open Collections 2
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Decart API
OPEN COLLECTIONDecart API
OPEN COLLECTIONMCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
Decart MCP Server
Decart publishes a hosted, remote MCP server on its documentation host. It is a documentation-knowledge server, not a wrapper over the Decart REST API: its three tools search an...
MCP SERVERPricing Plans 1
Published pricing tiers and plan structures.
Decart Plans Pricing
PLANSRate Limits 1
Documented rate limits and quota policies.
Decart Rate Limits
RATE LIMITSSecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
Recommended x-agentic-access execution contracts for AI agents.
Resources
Get Started 5
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 5
Pagination, idempotency, versioning, errors, and events
Build 6
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 6
Status, limits, changes, and where to get help
Commercial 4
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 6
Properties that don't map to a standard resource type
Source (apis.yml)
Work with this as data
Every provider here is available over the APIs.io API and to AI agents over MCP.