MiniMax H3
VideoMiniMax · Text to video · from $0.1
MiniMax H3 Text to Video generates coherent 2K videos from text prompts, with flexible 5-15 second duration and adaptive or custom aspect ratios for cinematic scenes, creative videos, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
This page covers the MiniMax H3 video model (open-sourced 2026-07-31, 2K/15s). The image model is a separate entry, MiniMax H3-Image (released 2026-11-10).
- Tasks: text-to-video and image-to-video, 2K, up to 15 seconds, native stereo audio.
- Open weights and self-hostable; check the official repo for VRAM and quantized builds.
- Shares the H3 prefix with H3-Image, but parameters, inputs and billing are different.
Worth knowing
Many results for “minimax h3 image” actually describe the video model’s image-to-video mode, not the H3-Image image model.
PromptExpand
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.
Parameters
Official parameters only. Explicit capabilities are limited to what the official description states.
| Dimension | MiniMax H3 |
|---|---|
| Task | Text to video |
| Starting price | $0.1/run · 5s |
| Resolution | 768p / 2k |
| Aspect ratio | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 |
| Duration | 5s |
| Explicit capabilities | Text to video |
Explicit capabilities are only those stated in the official description. Nothing is inferred.
Pricing
Beyond the starting price, resolution and duration change the actual cost.
| Model | Unit price | Resolution / duration | Source | Verified |
|---|---|---|---|---|
| MiniMax H3 | $0.1/run · 5s | 768p · 5s | wavespeed | 11/11/2026 |
Prices are official starting prices, excluding tax and FX. Refer to the official source.
Samples for this task
Official samples. Task and parameters are defined by the original page.
Speeder chase across a cliff city (single continuous shot) From a monumental cliffside city carved into stone, the camera dives toward a tiny streak of light ripping along a narrow ledge-road. Lock-on: a speeder hugging the wall at insane speed. The camera slingshots ahead, whips back, then drops tight to the rear thrusters: heat haze, grit snapping off the ledge, warning lights flashing. A collapsing balcony rains debris; the rider snaps a last-inch swerve under a falling arch, then threads through hanging laundry lines and open windows in one fluid line. The camera darts through the same openings, staying glued to the motion. One final bend and sudden calm: the camera blasts outward into a reveal of the city opening onto a boundless waterfall-fed valley, mist turning into rainbow.
A young woman in a long pale coat walks toward a small stone chapel on a windswept cliff above the ocean. The opening frame is a cinematic long-lens medium-wide shot with tall coastal grass softly blurred in the foreground. She is illuminated by a break in the clouds while the chapel and dark ocean remain slightly subdued behind her. She stops halfway along the path when the chapel bell rings once. A man appears briefly in the doorway, then steps back into darkness. The camera slowly tracks through the foreground grass, keeping her centered in the moving composition, then gently pushes toward the chapel. Poetic romantic mystery, dramatic coastal light, strong depth separation, natural wind, restrained acting, cinematic European drama aesthetic.
Other models of the same type
Same type, ready for a side-by-side comparison. This is not a ranking.
Data source
Prices and samples come from the wavespeed official model page; last verified 11/11/2026. This page currently includes 2 official samples. Prompts and parameters are defined by the original page.
Prices change with resolution, duration and official updates. This page shows starting prices and default configurations only; refer to the official source for actual cost.
FAQ
- Are MiniMax H3 and MiniMax H3-Image the same model?
- No. H3 is the video model (2K/15s/native stereo). H3-Image is the image model released 2026-11-10, with 16 MP output and up to 16 references.
- How much does MiniMax H3 cost?
- Video runs are billed per run; see the price table above. Resolution and duration change the actual cost. Last verified: 11/11/2026.
- Does MiniMax H3 support Chinese text?
- The official description does not explicitly list Chinese text capability. Validate with your actual copy before using it for Chinese text.
- What is the official task category for MiniMax H3?
- The official task category is Text to video (Text to Video API). This page only shows verifiable tasks, prices and parameters; it does not infer use cases.
- How should I choose between MiniMax H3 and similar models?
- Start with a side-by-side comparison of MiniMax H3 and Hailuo 2.3 T2V Pro: price, parameters and official samples on one page.