# Windflow > Windflow runs realtime interactive AI video models as on-demand sessions. Teams plug them into their products and pay by the session second. Windflow (Windflow Labs, https://windflow.online) is a developer platform for realtime interactive video and world models. A session keeps the model running: connect once, receive live frames, and send prompts, images, camera motion or actions over the same channel while the model keeps running. The API is REST for control (`/v1`) plus a media transport (WebSocket or WebRTC). Windflow is in private beta. Windflow Labs is not affiliated with other organisations that use the Windflow name: the AI-powered QA and UX testing product at windflow.io, the enterprise AI company at windflow.ai, the WindFlow C++ stream-processing library, or Windflow Technology, the wind-turbine company. ## Models 10 models are in the public catalog. Each speaks the same typed session protocol; what differs is the inputs and controls a model supports. - [Helios](https://windflow.online/models/helios): One continuous, steerable clip on the main_video track. Inputs: Text prompt (required before start) and an optional reference image for image-to-video. Architecture: 14B Diffusion Transformer, autoregressive chunked diffusion. $0.0017 per ready session-second. - [LongLive-2.0](https://windflow.online/models/longlive-2): A multi-shot clip on main_video; chunk_index resets per scene while session_chunk keeps counting. Inputs: Text shot prompts only — no reference image in this release. Architecture: Autoregressive multi-shot DiT (Wan2.2-TI2V backbone). $0.0021 per ready session-second. - [SANA-Streaming](https://windflow.online/models/sana-streaming): The edited stream on main_video, with original motion preserved. Inputs: A source clip you upload (≥ 41 frames) or a live webcam track, plus an edit prompt. Architecture: 2B streaming editing Diffusion Transformer. $0.0019 per ready session-second. - [JoyAI-Video-Edit](https://windflow.online/models/joyai-video-edit): The edited stream on main_video, with source motion and identity preserved. Inputs: A source clip you upload or a live webcam track, an edit instruction, and optionally a reference image. Architecture: 16B multimodal DiT, chunk-autoregressive, two-step distilled. $0.0021 per ready session-second. - [LingBot-World 2.0](https://windflow.online/models/lingbot): A navigable stream on main_video you steer in real time. Inputs: A seed image (uploadFile) and a text prompt, plus persistent WASD movement and look controls. Architecture: Seed-image conditioned navigable world model. $0.0024 per ready session-second. - [Matrix-Game 2.0](https://windflow.online/models/matrix-game-2): A navigable generated world stream on main_video. Inputs: A seed image and persistent WASD/look controls (no text prompt). Architecture: Real-time AR world model (SkyReels-V2 base, Self-Forcing distilled, 3-step). $0.0024 per ready session-second. - [DreamX-World-5B](https://windflow.online/models/dreamx-world-5b): A controllable world rollout on main_video. Inputs: A seed image, a text prompt, and movement/camera-control state. Architecture: 5B controllable world generation model (Wan2.2-TI2V backbone). $0.0023 per ready session-second. - [ABot-World-0-5B](https://windflow.online/models/abot-world-0-5b): A third-person navigable world stream on main_video. Inputs: A seed image, a text prompt, and persistent movement/camera key state. Architecture: 5B keyboard-conditioned world model (Wan2.2-TI2V backbone, LongForcing causal student). $0.0023 per ready session-second. - [MiniMax FastH3](https://windflow.online/models/fast-h3): Video on main_video and generated audio downmixed to mono on main_audio, aligned per window. Inputs: A text prompt with visual, dialogue, soundscape, and music direction. Architecture: 35B MiniMax H3 text-to-video-and-audio model, DMD2-distilled to four DiT calls with 90% sparse VSA-H3 attention. $0.0069 per ready session-second. - [LTX-2.5](https://windflow.online/models/ltx-2-5): Video on main_video and the audio generated with it on main_audio, aligned per window. Inputs: A text prompt and an optional reference still. Architecture: 22B joint audio+video DiT, two-stage, generated one window at a time. $0.0040 per ready session-second. ## Pricing Pay per ready session-second, from $0.0017 to $0.0069 depending on the model (indicative private-beta rates). The meter runs while a session is ready. Ready time is billable even when delivery is paused or unwatched; release the owner session to stop billing. Queueing and worker startup are free. No subscription, no seats, no minimums. Approved accounts start with $5 and 4 concurrent sessions. Details: https://windflow.online/pricing. ## Capacity Model capacity is brought up on demand. Live readiness per model is at https://api.windflow.online/v1/status (no auth). To see a model running, ask for a live demo. ## Guides - [How per-second pricing works for realtime video, with worked examples](https://windflow.online/guides/how-per-second-pricing-works): Understand ready-second video API billing, compare model rates and estimate session costs. Queueing and startup are free; release sessions to stop billing. - [How to add live AI video to your app and pay per second](https://windflow.online/guides/add-live-ai-video-to-your-app): Add live AI video to your product: choose a model, connect a session, stream frames, send controls and estimate ready-second costs with Windflow. - [How to host LingBot-World as a realtime API](https://windflow.online/guides/host-lingbot-world-api): Run LingBot-World through a hosted API or evaluate self-hosting. Learn seed inputs, persistent movement, session costs and checks for an interactive app. - [How to measure realtime video API latency and responsiveness](https://windflow.online/guides/measure-realtime-video-latency): Measure first-frame time, control-to-visible delay, delivered FPS and stalls. Evaluate a realtime video or world model through the client your users see. - [How to turn an open-source video model into a realtime API](https://windflow.online/guides/turn-an-open-source-video-model-into-a-realtime-api): Prepare a video model for a hosted realtime API: licensed weights, repeatable inference, streaming transport, session controls and measured performance. - [Realtime AI video on AMD GPUs: reading MI355X benchmarks](https://windflow.online/guides/realtime-video-generation-amd-gpus): Read Windflow's AMD MI355X video inference measurements with the right context: GPU count, resolution, generated windows, edit latency and runtime limits. - [Realtime video API: generate, edit and control live AI video](https://windflow.online/guides/realtime-video-api): Choose a realtime video API for continuous generation, webcam editing or interactive worlds. Compare controls, latency, session lifecycle and usage costs. - [Streaming a video diffusion model to the browser: WebRTC or WebSocket?](https://windflow.online/guides/stream-video-diffusion-webrtc-websocket): Deliver streaming video diffusion to the browser with WebRTC or WebSocket. Understand generation chunks, network trade-offs and visible latency. - [World model API: embed a navigable AI world in your app](https://windflow.online/guides/world-model-api): Embed navigable AI worlds with a hosted world model API. Compare LingBot, Matrix-Game, DreamX and ABot inputs, movement controls and integration limits. ## Comparisons - [DreamX-World-5B vs ABot-World-0-5B: inputs, controls and API cost](https://windflow.online/compare/dreamx-world-5b-vs-abot-world-0-5b): Compare DreamX-World-5B and ABot-World-0-5B APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Helios vs LongLive vs LTX-2.5: choose a realtime video model](https://windflow.online/compare/helios-vs-longlive-vs-ltx): Choose Helios for continuous scenes, LongLive for shot direction or LTX-2.5 for video with sound. Compare control timing and inputs before integration. - [Helios vs LongLive-2.0: inputs, controls and API cost](https://windflow.online/compare/helios-vs-longlive-2): Compare Helios and LongLive-2.0 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Helios vs LTX-2.5: inputs, controls and API cost](https://windflow.online/compare/helios-vs-ltx-2-5): Compare Helios and LTX-2.5 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Helios vs MiniMax FastH3: inputs, controls and API cost](https://windflow.online/compare/helios-vs-fast-h3): Compare Helios and MiniMax FastH3 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [LingBot-World 2.0 vs ABot-World-0-5B: inputs, controls and API cost](https://windflow.online/compare/lingbot-vs-abot-world-0-5b): Compare LingBot-World 2.0 and ABot-World-0-5B APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [LingBot-World 2.0 vs DreamX-World-5B: inputs, controls and API cost](https://windflow.online/compare/lingbot-vs-dreamx-world-5b): Compare LingBot-World 2.0 and DreamX-World-5B APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [LingBot-World 2.0 vs Matrix-Game 2.0: inputs, controls and API cost](https://windflow.online/compare/lingbot-vs-matrix-game-2): Compare LingBot-World 2.0 and Matrix-Game 2.0 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [LongLive-2.0 vs LTX-2.5: inputs, controls and API cost](https://windflow.online/compare/longlive-2-vs-ltx-2-5): Compare LongLive-2.0 and LTX-2.5 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [LongLive-2.0 vs MiniMax FastH3: inputs, controls and API cost](https://windflow.online/compare/longlive-2-vs-fast-h3): Compare LongLive-2.0 and MiniMax FastH3 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Managed platform, rented GPU or self-hosting: how to run a realtime video model](https://windflow.online/compare/managed-platform-vs-rented-gpu-vs-self-hosting): Compare managed APIs, rented GPUs and self-hosting for realtime video models. Understand session costs, infrastructure work and when each approach fits. - [Matrix-Game 2.0 vs ABot-World-0-5B: inputs, controls and API cost](https://windflow.online/compare/matrix-game-2-vs-abot-world-0-5b): Compare Matrix-Game 2.0 and ABot-World-0-5B APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Matrix-Game 2.0 vs DreamX-World-5B: inputs, controls and API cost](https://windflow.online/compare/matrix-game-2-vs-dreamx-world-5b): Compare Matrix-Game 2.0 and DreamX-World-5B APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [MiniMax FastH3 vs LTX-2.5: inputs, controls and API cost](https://windflow.online/compare/fast-h3-vs-ltx-2-5): Compare MiniMax FastH3 and LTX-2.5 APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Realtime video APIs vs batch video generation: which fits?](https://windflow.online/compare/realtime-video-api-vs-batch-generation): Choose live sessions or completed video jobs by interaction, latency and cost. Understand streaming output, state, controls and when to use both patterns. - [SANA-Streaming vs JoyAI-Video-Edit: inputs, controls and API cost](https://windflow.online/compare/sana-streaming-vs-joyai-video-edit): Compare SANA-Streaming and JoyAI-Video-Edit APIs: inputs, outputs, streaming delivery and ready-second cost. Choose a Windflow model for your product. - [Windflow vs fal: choosing an API for interactive AI video](https://windflow.online/compare/windflow-vs-fal): Compare Windflow sessions with fal queue and realtime endpoints. Choose by model behavior, live controls, streaming output and the product you need to build. - [Windflow vs Reactor for realtime video and world model APIs](https://windflow.online/compare/windflow-vs-reactor): Compare Windflow and Reactor for live video and world model applications: session contracts, SDKs, model controls, readiness and an evaluation checklist. - [Windflow vs Replicate: model predictions or live video sessions](https://windflow.online/compare/windflow-vs-replicate): Compare a prediction-based model integration with a live Windflow session. Understand output files, SSE streams, persistent controls and application state. ## Use cases - [Build a shared AI video live stream for an audience](https://windflow.online/use-cases/shared-ai-video-live-stream): Stream one generated AI video session to authorized viewers. Design host controls, audience input, session ownership, billing and recording boundaries. - [Infinite streaming video generation: continuous video that keeps going](https://windflow.online/use-cases/infinite-streaming-video-generation): Build continuous AI video streams with hosted realtime models. Compare prompt control, generation windows and session limits for channels and displays. - [Interactive AI storytelling with realtime video models](https://windflow.online/use-cases/interactive-ai-storytelling): Build a story users can direct while it plays. Choose scene or shot controls, keep narrative state in your app and budget realtime video sessions. - [Live video editing from a webcam with a text instruction](https://windflow.online/use-cases/live-video-editing-from-a-webcam): Edit a live webcam or uploaded clip using text instructions. Compare SANA-Streaming and JoyAI-Video-Edit inputs, reference conditioning and responsiveness. - [Navigable world models for games: an API with WASD control](https://windflow.online/use-cases/navigable-world-models-for-games): Build navigable game scenes from a seed image with hosted world models. Compare movement, look, prompt conditioning and continuity limits on Windflow. ## Video prompts - [AI product video prompts](https://windflow.online/prompts/product-video-prompts): Explore ai product video prompts with copyable templates, source input guidance, camera choices and practical checks for motion and continuity. - [Alpine trail world model prompt](https://windflow.online/prompts/world-alpine-trail): Copy this alpine trail world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Ancient ruins world model prompt](https://windflow.online/prompts/world-ancient-ruins): Copy this ancient ruins world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Cinematic AI video prompts](https://windflow.online/prompts/cinematic-video-prompts): Explore cinematic ai video prompts with copyable templates, source input guidance, camera choices and practical checks for motion and continuity. - [Cinematic alpine lake video prompt](https://windflow.online/prompts/cinematic-alpine-lake): Copy this cinematic alpine lake video template. Find source guidance, a simpler variation and motion checks for your video model. - [Coffee pour AI video prompt](https://windflow.online/prompts/product-coffee-pour): Copy this coffee pour ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Cyberpunk alley world model prompt](https://windflow.online/prompts/world-cyberpunk-alley): Copy this cyberpunk alley world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Desert tracking shot video prompt](https://windflow.online/prompts/cinematic-desert-tracking): Copy this desert tracking shot video template. Find source guidance, a simpler variation and motion checks for your video model. - [Fantasy village world model prompt](https://windflow.online/prompts/world-fantasy-village): Copy this fantasy village world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Headphone orbit AI video prompt](https://windflow.online/prompts/product-headphone-orbit): Copy this headphone orbit ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Interactive world model prompts](https://windflow.online/prompts/worlds-video-prompts): Explore interactive world model prompts with copyable templates, source input guidance, camera choices and practical checks for motion and continuity. - [Live AI jacket recolor video prompt](https://windflow.online/prompts/live-video-neon-jacket): Copy this live ai jacket recolor video template. Find source guidance, a simpler variation and motion checks for your video model. - [Live AI video editing prompts](https://windflow.online/prompts/editing-video-prompts): Explore live ai video editing prompts with copyable templates, source input guidance, camera choices and practical checks for motion and continuity. - [Live AI video night lighting prompt](https://windflow.online/prompts/live-video-night-lighting): Copy this live ai video night lighting template. Find source guidance, a simpler variation and motion checks for your video model. - [Live video clay character prompt](https://windflow.online/prompts/live-video-clay-character): Copy this live video clay character template. Find source guidance, a simpler variation and motion checks for your video model. - [Live video comic style prompt](https://windflow.online/prompts/live-video-comic-style): Copy this live video comic style template. Find source guidance, a simpler variation and motion checks for your video model. - [Live video garden background prompt](https://windflow.online/prompts/live-video-background-garden): Copy this live video garden background template. Find source guidance, a simpler variation and motion checks for your video model. - [Live video watercolor editing prompt](https://windflow.online/prompts/live-video-watercolor): Copy this live video watercolor editing template. Find source guidance, a simpler variation and motion checks for your video model. - [Lunar outpost world model prompt](https://windflow.online/prompts/world-lunar-outpost): Copy this lunar outpost world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Neon rainy street AI video prompt](https://windflow.online/prompts/cinematic-neon-rain): Copy this neon rainy street ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Perfume bottle AI product video prompt](https://windflow.online/prompts/product-perfume-bottle): Copy this perfume bottle ai product video template. Find source guidance, a simpler variation and motion checks for your video model. - [Skincare texture AI video prompt](https://windflow.online/prompts/product-skincare-texture): Copy this skincare texture ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Sneaker reveal AI video prompt](https://windflow.online/prompts/product-sneaker-reveal): Copy this sneaker reveal ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Space station cinematic video prompt](https://windflow.online/prompts/cinematic-space-station): Copy this space station cinematic video template. Find source guidance, a simpler variation and motion checks for your video model. - [Underwater city world model prompt](https://windflow.online/prompts/world-underwater-city): Copy this underwater city world model template. Find source guidance, a simpler variation and motion checks for your video model. - [Underwater reef AI video prompt](https://windflow.online/prompts/cinematic-underwater-reef): Copy this underwater reef ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Watch macro AI video prompt](https://windflow.online/prompts/product-watch-macro): Copy this watch macro ai video template. Find source guidance, a simpler variation and motion checks for your video model. - [Wildlife close-up AI video prompt](https://windflow.online/prompts/cinematic-wildlife-portrait): Copy this wildlife close-up ai video template. Find source guidance, a simpler variation and motion checks for your video model. Public product pages, model pages, guides, comparisons, prompt recipes, free tools, use cases and field notes are available as Markdown: append `.md` to the URL (use `/index.md` for the homepage), or send `Accept: text/markdown`. ## Free tools - [AI video API cost calculator](https://windflow.online/tools/ai-video-cost-calculator): Calculate realtime AI video API cost by model, session duration and concurrent users. Compare published rates with a free browser-based estimator. - [AI video prompt generator](https://windflow.online/tools/ai-video-prompt-generator): Build a video prompt from a subject, action, camera move, lighting and visual style. Copy the result and explore practical AI video prompt examples. - [AI video and world model selector](https://windflow.online/tools/ai-video-model-selector): Find a hosted AI video or world model by text, image, camera, movement and audio requirements. Compare supported inputs and published session pricing. - [Video streaming bandwidth calculator](https://windflow.online/tools/video-bandwidth-calculator): Estimate video streaming data use from bitrate, duration and viewers. Convert Mbps to GB per hour and calculate audience bandwidth in your browser. - [Video frame count calculator](https://windflow.online/tools/video-frame-calculator): Convert video duration and frame rate into frame count. Estimate generation chunks, playback time and frame budgets with a free browser calculator. - [Video latency budget calculator](https://windflow.online/tools/video-latency-calculator): Estimate a video latency budget from generation, network, buffering and decoding. See each component's share and plan a measurable response-time target. ## Full public reference - [Full public text](https://windflow.online/llms-full.txt): public product facts, model specifications, guides, comparisons, use cases and field notes in one file; no account required. - [Sitemap](https://windflow.online/sitemap.xml): canonical HTML pages and source modification dates. ## Get access - Request access: https://windflow.online/auth - Email: hello@windflow.online - Bring your own model: https://windflow.online/bring-a-model ## Pages - [Platform](https://windflow.online/platform): how sessions, control and metering work - [Models](https://windflow.online/models): the public model catalog - [Pricing](https://windflow.online/pricing): per-second rates and the FAQ - [Blog](https://windflow.online/blog): engineering field notes ([RSS](https://windflow.online/blog/rss)) - [About](https://windflow.online/about): who Windflow Labs is, and which other Windflows it is not - [FAQ](https://windflow.online/faq) and [Glossary](https://windflow.online/glossary): short answers and definitions - [X](https://x.com/windflowlabs) - [LinkedIn](https://www.linkedin.com/company/windflow-labs/) - [GitHub](https://github.com/windflow-labs) ## API documentation The full API reference, per-model command schemas and the Markdown docs index are served to Windflow accounts. Send `Authorization: Bearer ` to https://windflow.online/llms.txt for the docs index and to https://windflow.online/llms-full.txt for everything in one file.