MiniMax H3 API

MiniMax H3 — text-to-video, image-to-video, and reference-to-video in one model. 2K output, 5-15s, native synced audio. Integrate this model via REST with endpoint docs, parameters, and code examples.

Prompting guide Compare video models Use cases

Video Generation

Img2Vid

Audio

Credit Cost

15 credits

Type

Video

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

API Endpoint

POST

/api/v1/models/minimax-h3/run

Test This Model

Run a real request through the API pipeline and inspect the exact input and output your integration will handle. Uses your credits like any API call; failed runs are refunded automatically.

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/minimax-h3.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`prompt` required	string	Text description of the video, motion, and sound to generate	-
`image_url`	url	First-frame image. Switches to image-to-video mode.	-
`end_image_url`	url	Last-frame image. Requires image_url.	-
`reference_images`	string	Up to 9 image URLs that guide subject and scene identity. Cannot be combined with image_url / end_image_url.	-
`aspect_ratio`	enum	Output aspect ratio (2K). Ignored in image-to-video mode — the start frame sets the aspect. `16:94:31:19:163:4`+1 more	`16:9`
`duration`	integer	Video duration in seconds (5-15) min: 5 \| max: 15	`5`
`seed`	integer	Random seed for reproducibility	-

Supported Aspect Ratios

16:9

4:3

1:1

9:16

3:4

21:9

Example Outputs

Real outputs generated by this model

View Details

Joey and Chandler sit side by side on the couch with coffee cups. Joey turns to Chandler with a completely sincere, concerned expression. DIALOGUE: JOEY: “Could AI replace us?” Chandler slowly looks up from his coffee. Pauses. Looks Joey dead in the eye. CHANDLER: “Joey, AI cannot replace you. Nothing can replace you. Well, except Pixel Dojo.” Joey nods slowly. Visibly relieved. Processing. JOEY: “Because It's too good?” Chandler stares at him. Long beat. He looks down at his coffee, then back up. CHANDLER: “…That's right. It just is.” STYLE: Warm 90s sitcom aesthetic, steady handheld feel, natural performances, characters in casual clothing. Joey played completely straight — zero irony. Chandler delivers every line with exhausted deadpan sarcasm. Hold on Chandler’s face after the final line for a full beat before cut.”

0 credits

Code Examples

Text → video — copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/minimax-h3/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A lighthouse keeper climbs the spiral stairs at dawn, waves crashing below",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 15,
  "creditsRemaining": 95,
  "expiresAt": "2026-08-08T19:39:46Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "video": "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.mp4"
  },
  "creditCost": 15,
  "expiresAt": "2026-08-08T19:39:46Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits