← All models
H3 Max Multi Angle turns a single image into a video with precise, keyframe-based control over the camera's orbit, elevation, and distance in 3D space
Example
Details
- Accepts
- text
Pricing
- Price
- 1.56 cr / second
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | — | Random seed. A random seed is selected when omitted. |
| prompt | string | Text prompt for video generation. When omitted or blank, defaults to preserving the frozen reference scene while only the camera moves. |
| duration | integer | The duration of the video in seconds. |
| image_urlrequired | string | URL of the image to use as the first frame. |
| sync_mode | boolean | Return the generated video as base64 instead of a CDN URL. |
| resolution | stringenum: 480P, 768P, 1080P | The native generation resolution, or 1080P latent refinement from a native 768P source. |
| camera_trajectory | array | Ordered camera keyframes. The first pose is held before its time and the final pose is held for the remainder of the video. Signed full turns are preserved, with at most 32 turns of total azimuth travel. |
| enable_safety_checker | boolean | If set to true, the safety checker will be enabled. |
| prompt_expansion_moderequired | string | How much effort to spend rewriting the prompt before generation. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt. |
Output
| Field | Type | Description |
|---|---|---|
| video | — | The generated video |
| timings | — | Timing breakdown in seconds. 'inference' is the DiT denoising time on the GPU backend. Null on routes that do not report backend timings. |
| expanded_prompt | — | The prompt after expansion, as sent to the model. Null when prompt expansion was disabled, left the prompt unchanged, or was performed internally by MiniMax's hosted API. |