← Models
Realtime video generation
Helios API
One continuous, steerable clip on the main_video track. Served on Windflow as a realtime session you can plug into your product and pay for by the second.
Windflow session capture
Overview
What Helios does
Helios is a 14-billion-parameter, open-source video diffusion model from the PKU-YuanGroup research lab, built to generate long video continuously rather than as a fixed-length clip. On Windflow it runs as a realtime session: you set the opening prompt, start the stream, and keep steering the same continuous clip while frames arrive live.
A session keeps the model running: connect once, steer it with text prompts and a reference image while it runs, and receive the live stream back on a named output track.
Every model in the catalog speaks the same typed session protocol, so switching between models changes the controls you send, not how you integrate.
- Architecture
- 14B Diffusion Transformer, autoregressive chunked diffusion
- Resolution
- Negotiated per session
- Playout
- Negotiated per session
- Chunk
- 33 native frames in the production profile
- Control latency
- First chunk after roughly one chunk of generation
- Inputs
- Text prompt (required before start) and an optional reference image for image-to-video
- Outputs
- One continuous, steerable clip on the main_video track
- Delivery
- WebSocket (H.264) · WebRTC
- Session protocol
- sdk.realtime.v2
- Price
- $0.0017 per billable second
$0.0017
Per billable second
Meter starts when generation begins
$6.12
Per billable hour
The same rate, held for an hour
Production
Runtime status
Capacity is brought up on demand
Private beta
Access
Request access or a live demo
Use cases
What teams build with Helios
- Continuous generative video for ambient scenes, live backdrops and long takes within a session's limits.
- Prompt-steered storytelling where each prompt change continues the scene instead of cutting away.
- Image-to-video runs that start from a reference image and keep going.
- Prototyping interactive video products before committing to a heavier world model.
Provenance
Where Helios comes from
The model and its code are published by the upstream authors. Windflow runs it behind one session API and bills per billable second.
- PKU-YuanGroup/Helios on GitHubLicence · Apache-2.0
Compare
Helios next to similar models
| Model | Inputs | Output | Price per billable second |
|---|---|---|---|
| Helios | Text prompt (required before start) and an optional reference image for image-to-video | One continuous, steerable clip on the main_video track | $0.0017 |
| LongLive-2.0 | Text shot prompts only — no reference image in this release | A multi-shot clip on main_video; chunk_index resets per scene while session_chunk keeps counting | $0.0021 |
| MiniMax FastH3 | A text prompt with visual, dialogue, soundscape, and music direction | Video on main_video and generated audio downmixed to mono on main_audio, aligned per window | $0.0069 |
| LTX-2.5 | A text prompt and an optional reference still | Video on main_video and the audio generated with it on main_audio, aligned per window | $0.0040 |
FAQ
Questions about Helios
- Can I change the prompt while Helios is running?
- Yes. set_prompt updates the running session while retaining latent scene memory; it does not guarantee unchanged subjects or geometry. Use scene_cut when you intend to clear that memory and start independent content.
- Can Helios start from an image?
- Yes. A reference image is optional and turns the run into image-to-video. A text prompt is required before the stream starts, because it anchors the first chunk.
- Does prompt_accepted mean the new scene is already visible?
- No. It acknowledges an ordered revision. prompt_applied identifies a model-conditioning boundary, and content_visible reports the first presented frame of the corresponding content epoch on the supported WebSocket path. Measure those stages separately.
- Can Helios edit a live webcam feed?
- The published Helios profile generates from text and an optional reference image; it does not accept a source clip or webcam track. Evaluate SANA-Streaming or JoyAI-Video-Edit for live source-video editing.
- How much does Helios cost on Windflow?
- Helios costs $0.0017 per billable session-second ($6.12/hr of billable time). Billing starts at the session's first generation_started event and stops when the session is released or ends. Queueing, worker startup, time before generation starts and the documented reconnect grace are not billed. After generation starts, paused or unwatched time remains billable; release the owner session to stop the meter. There is no subscription.
- How do I get access to Helios?
- Windflow is in private beta. Request access from the sign-up page, or ask for a live demo of Helios. Approved accounts start with $5 and four concurrent sessions.
- Is Helios always running?
- No. Model capacity is brought up on demand rather than kept standing. Live readiness for each model is published at api.windflow.online/v1/status, and a live demo can be arranged on request.
Guides and comparisons
- Live audience use caseBuild a shared AI video live stream for an audience
- GuideChoosing a realtime video model: a decision guide for 12 hosted models
- Model comparisonHelios vs LongLive vs LTX-2.5: choose a realtime video model
- GuideHow per-second pricing works for realtime video, with worked examples
- GuideHow to add live AI video to your app and pay per second
- Evaluation guideHow to measure realtime video API latency and responsiveness
- Model API guideHow to use the Helios API
- Cost comparisonRealtime video API pricing: compare rates and billable timelines
- API guideRealtime video API: generate, edit and control live AI video
- GuideStreaming a video diffusion model to the browser: WebRTC or WebSocket?
- Endpoint comparisonWindflow vs fal: choosing the right realtime video endpoint
- Platform comparisonWindflow vs Reactor: choosing a realtime model session API
- Prompt guideHelios prompting guide: write and steer a live video
- Use caseInfinite streaming video generation: continuous video that keeps going
- Integration comparisonRealtime video APIs vs batch video generation: which fits?
- Troubleshooting guideHow to recover a realtime video stream after a dropped connection
- GuideHow realtime video models work: autoregressive diffusion, chunks and the latency budget
- Storytelling use caseInteractive AI storytelling with realtime video models
Other models
Realtime video generationLongLive-2.0Live video transformationSANA-StreamingLive video transformationEdenLiveLive video transformationJoyAI-Video-EditNavigable world modelLingBot-World 2.0Neural game renderingMatrix-Game 4.0Navigable world modelDreamX-World-5BNavigable world modelABot-World-0-5BRealtime video generationMiniMax FastH3Realtime video generationLTX-2.5Navigable world modelHy-Nomas