MCP / Models / Image to video
MiniMax H3 Max Camera Controls MCP: move the camera
MiniMax H3 Max Camera Controls turns one picture into a video where only the camera moves, on a preset or your own keyframes. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

$ YOUR NEXT RUN
Use MiniMax H3 Max Camera Controls in your assistant
Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/minimax-h3-max-camera-controls.md. Help me connect the FlyMy.AI MCP to this assistant, then run MiniMax H3 Max Camera Controls (flymyai/minimax-h3-max-camera-controls) for this task: Turn the product photo I attach into a slow camera reveal with MiniMax H3 Max Camera Controls: the camera dollies in and the scene stays still.
What MiniMax H3 Max Camera Controls does
Send image, the first frame, and, if you like, prompt; left out, the model keeps the scene frozen and moves only the camera. free_camera_preset picks a ready move: truck right or left, pedestal up or down, dolly in or out, pan right or left, tilt up or down, roll right or left, or s_curve_forward. For a path of your own send camera_trajectory: 2 to 12 keyframes, each with time (0 at the start of the clip to 1 at its end), azimuth (degrees around the subject), elevation (-90 to 90 degrees) and distance (above 0, smaller is closer); a preset wins over keyframes. duration is 1 to 15 seconds (5 by default), resolution is 480P (the default), 768P or 1080P, and prompt_expansion_mode and seed work as in the other H3 Max models. Outputs: video, one MP4 clip, and expanded_prompt. It is also known as H3 Max Multi Angle.
It is billed per second of video you ask for, more at a higher resolution. It does not make a video from text alone (MiniMax H3 Max Text to Video does) and does not take a camera path exported from Blender.
If a picture shows a real person, use it only with their consent.
MiniMax H3 Max Camera Controls inputs
Every input of flymyai/minimax-h3-max-camera-controls as its live schema lists them. Returns video (array), expanded_prompt (string).
| Input | Type, values and default |
|---|---|
# image | file required Allowed: image file, as a URL or upload The picture to film: it becomes the first frame, a link or an upload; use a real person's picture only with their permission |
# prompt | string optional Optional: what the scene looks like or what happens; left out, the model keeps the scene frozen and moves only the camera |
# duration | integer optional Allowed: 1 to 15 Default: 5 Length of the clip in seconds, 1-15; the price is per second ($0.05 at 480P, $0.08 at 768P, $0.16 at 1080P). The finished clip can run up to about 0.7 seconds longer than you ask for; the price counts the seconds you ask for |
# resolution | string optional Allowed: 480P, 768P, 1080P Default: 480P 480P ($0.05 a second), 768P ($0.08) or 1080P ($0.16, refined from a native 768P render) |
# free_camera_preset | string optional Allowed: truck_right, truck_left, pedestal_up, pedestal_down, dolly_in, dolly_out, pan_right, pan_left, tilt_up, tilt_down, roll_right, roll_left, s_curve_forward Optional ready camera move: truck (slide sideways), pedestal (up or down), dolly (in or out), pan and tilt (turn in place), roll (around the lens axis) or s_curve_forward. When set, camera_trajectory is ignored |
# camera_trajectory | string optional Optional: your own camera path as a JSON list of 2 to 12 keyframes, each {"time": 0 to 1 (the start to the end of the clip), "azimuth": degrees around the subject, "elevation": -90 to 90 degrees, "distance": above 0, smaller is closer}, for example [{"time":0,"azimuth":0,"elevation":0,"distance":1},{"time":1,"azimuth":90,"elevation":10,"distance":0.6}]. The first pose is held before its time and the last one after it |
# prompt_expansion_mode | string optional Allowed: disabled, balanced, quality Default: balanced How much effort goes into rewriting your prompt before the video is made: disabled (your words as they are), balanced (about a second, the default) or quality (up to about 30 seconds, a richer prompt). No price effect |
# seed | integer optional Allowed: 0 to 2147483647 Seed for the generation; a random one is used when you leave it out |
Ask your agent
Requests to paste as they are, once the FlyMy.AI MCP is connected.
flymyai/minimax-h3-max-camera-controlsflymyai/minimax-h3-max-camera-controlsflymyai/minimax-h3-max-camera-controlsMiniMax H3 Max Camera Controls price
From $0.05 per second of duration, depending on resolution. A run at the default settings costs $0.25. A run costs $0.05 to $2.40, depending on duration and resolution. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.
| Setting | Price |
|---|---|
| resolution 480P | $0.05 per second |
| resolution 768P | $0.08 per second |
| resolution 1080P | $0.16 per second |
Call MiniMax H3 Max Camera Controls from code
The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.
From an agent, through the MCP
The agent calls get_model_schema, then run_model with:
{
"endpoint_id": "flymyai/minimax-h3-max-camera-controls",
"input": {
"prompt": "Slow camera push-in with gentle, natural motion in the scene",
"image": "https://example.com/photo.jpg"
}
}From your code, over HTTP
Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-camera-controls/predict/async/result/?request_id=<prediction_id>.
curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-camera-controls/predict/async/ \
-H "X-API-KEY: $FLYMYAI_API_KEY" \
-F 'prompt=Slow camera push-in with gentle, natural motion in the scene' \
-F "image=@photo.jpg"Questions about MiniMax H3 Max Camera Controls
Do I need a MiniMax API key for MiniMax H3 Max Camera Controls?
No. MiniMax H3 Max Camera Controls runs on FlyMy.AI's account, so you need no MiniMax key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.
How much does MiniMax H3 Max Camera Controls cost?
From $0.05 per second of duration, depending on resolution. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.
How do I use MiniMax H3 Max Camera Controls in Claude Code, Codex or Cursor?
Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Turn the product photo I attach into a slow camera reveal with MiniMax H3 Max Camera Controls: the camera dollies in and the scene stays still." Your agent reads the inputs with get_model_schema and runs flymyai/minimax-h3-max-camera-controls with run_model.
What does MiniMax H3 Max Camera Controls need as input?
MiniMax H3 Max Camera Controls requires image; it also takes 7 optional inputs, each listed on this page with its allowed values and default.
Can I call MiniMax H3 Max Camera Controls from my own code?
Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/minimax-h3-max-camera-controls/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.
Go to the source
From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.





