MCP / Models / Text to video

MiniMax H3 Text to Video MCP: 2K video with audio

MiniMax H3 Text to Video renders native 2K video with audio from a prompt, 4 to 15 seconds long, at a low price per second. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

Use MiniMax H3 Text to VideoInputs and price
No API keyfrom $0.08 / sText to videoMiniMaxCommercial use
MiniMax H3 Text to Video sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use MiniMax H3 Text to Video 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-t2v.md. Help me connect the FlyMy.AI MCP to this assistant, then run MiniMax H3 Text to Video (flymyai/minimax-h3-t2v) for this task: Make a 10-second video of a paper airplane flying over a city at dusk with MiniMax H3 Text to Video at 2K.
Open FlyMy.AIDownload brief

What MiniMax H3 Text to Video does

Pick resolution 768P or 2K and a duration from 4 to 15 seconds; prompt_optimizer rewrites a short prompt into a fuller one and is on by default. An optional first_frame_image opens the video with your picture.

MiniMax H3 Text to Video inputs

Every input of flymyai/minimax-h3-t2v as its live schema lists them. Returns output (array).

InputType, values and default
# prompt
string required
# prompt_optimizer
boolean required Default: true
# duration
integer required Allowed: 4 to 15 Default: 6
# resolution
string required Allowed: 768P, 2K Default: 768P
# first_frame_image
file optional Allowed: image file, as a URL or upload
# fast_pretreatment
boolean optional

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Make a 10-second video of a paper airplane flying over a city at dusk with MiniMax H3 Text to Video at 2K.”runs flymyai/minimax-h3-t2v
“Write and render a short ad for noise-cancelling earbuds with MiniMax H3 Text to Video: three quick shots ending on the product.”runs flymyai/minimax-h3-t2v
“Generate a calm, slow-camera clip of rain on a neon-lit street, a cyclist passing with MiniMax H3 Text to Video.”runs flymyai/minimax-h3-t2v

MiniMax H3 Text to Video price

From $0.08 per second of duration, depending on resolution. A run at the default settings costs $0.48. A run costs $0.32 to $1.95, depending on resolution and duration. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

SettingPrice
resolution 768P$0.08 per second
resolution 2K$0.13 per second

See usage pricing →

Call MiniMax H3 Text to Video 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-t2v",
  "input": {
    "prompt": "Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in",
    "prompt_optimizer": "true",
    "duration": "6",
    "resolution": "768P"
  }
}

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-t2v/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/minimax-h3-t2v/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Steam rises from a ceramic mug on a sunlit kitchen counter, slow camera push-in' \
  -F 'prompt_optimizer=true' \
  -F 'duration=6' \
  -F 'resolution=768P'

Questions about MiniMax H3 Text to Video

Do I need a MiniMax API key for MiniMax H3 Text to Video?

No. MiniMax H3 Text to Video 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 Text to Video cost?

From $0.08 per second of duration, depending on resolution. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-09.

How do I use MiniMax H3 Text to Video in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Make a 10-second video of a paper airplane flying over a city at dusk with MiniMax H3 Text to Video at 2K." Your agent reads the inputs with get_model_schema and runs flymyai/minimax-h3-t2v with run_model.

What does MiniMax H3 Text to Video need as input?

MiniMax H3 Text to Video requires prompt, prompt_optimizer, duration and resolution; it also takes 2 optional inputs, each listed on this page with its allowed values and default.

Can I call MiniMax H3 Text to Video from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/minimax-h3-t2v/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

Go to the source

MiniMax H3 Text to Video in the playground →Model endpoints in the docs →Text to video guide →Every model on FlyMy.AI →Every MCP in the catalog →Usage pricing →

From the FlyMy.AI model catalog of 2026-11-09: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.