Realtime video generation
MiniMax FastH3 API
Video on main_video and generated audio downmixed to mono on main_audio, aligned per window. Served on Windflow as a realtime session you can plug into your product and pay for by the second.
Overview
What MiniMax FastH3 does
MiniMax FastH3 is the 35-billion-parameter MiniMax H3 text-to-video-and-audio model, distilled to four DiT calls and sparse attention with the open-source FastVideo stack from Hao AI Lab. On Windflow it streams video with generated audio window by window from a text prompt that carries visual, dialogue, soundscape and music direction.
A session keeps the model running: connect once, steer it with text prompts 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
- 35B MiniMax H3 text-to-video-and-audio model, DMD2-distilled to four DiT calls with 90% sparse VSA-H3 attention
- Resolution
- 960 × 544
- Playout
- 24
- Chunk
- 345 frames per window (14.38 s at 24 fps; published as the 15 s profile)
- Control latency
- A whole window. The pipeline materialises the clip before delivery, so time-to-first-frame equals one generation.
- Inputs
- A text prompt with visual, dialogue, soundscape, and music direction
- Outputs
- Video on main_video and generated audio downmixed to mono on main_audio, aligned per window
- Delivery
- WebRTC
- Session protocol
- sdk.realtime.v2
- Price
- $0.0069 per billable second
$0.0069
Per billable second
Meter starts when generation begins
$25.00
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 MiniMax FastH3
- Generated video with synchronised dialogue, ambience and music from one prompt.
- Continuous AI channels and episodic streams built window by window.
- Short-form portrait or landscape clips for social and marketing tests.
- Evaluating MiniMax H3 behind a session API before committing to it.
Provenance
Where MiniMax FastH3 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.
- hao-ai-lab/FastVideo on GitHubLicence · Apache-2.0 (framework)
Compare
MiniMax FastH3 next to similar models
| Model | Inputs | Output | Price per billable second |
|---|---|---|---|
| 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 |
| 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 |
| 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 MiniMax FastH3
- Which licence covers FastH3?
- The MiniMax H3 Community License governs the model, including its territory and AI-generation disclosure terms. Read it before building a product on FastH3.
- Can I steer FastH3 mid-window?
- No. Each command lands at the next window boundary; prompt changes wait for the window in flight. Soft continuations carry the previous window's final frame forward.
- How much does MiniMax FastH3 cost on Windflow?
- MiniMax FastH3 costs $0.0069 per billable session-second ($25.00/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 MiniMax FastH3?
- Windflow is in private beta. Request access from the sign-up page, or ask for a live demo of MiniMax FastH3. Approved accounts start with $5 and four concurrent sessions.
- Is MiniMax FastH3 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
- 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
- Evaluation guideHow to measure realtime video API latency and responsiveness
- RadarRealtime models radar: week of October 5, 2026
- API guideRealtime video API: generate, edit and control live AI video
- Use caseInfinite streaming video generation: continuous video that keeps going
- GuideHow realtime video models work: autoregressive diffusion, chunks and the latency budget
- Storytelling use caseInteractive AI storytelling with realtime video models
Other models