MiniMax H3 Reference to Video API API: AI Image-to-Video

MiniMax H3 Reference to Video API API Reference

Endpoint

POST https://api.muapi.ai/api/v1/minimax-h3-reference-to-video

Submit a job with your MuApi API key in the x-api-key header, then poll https://api.muapi.ai/api/v1/predictions/{request_id}/result until status is completed.

Parameters

Name	Type	Required	Description
prompt	string	Yes	Describe the video scene and how the references should be used.
duration	integer	No	Output duration in seconds.Options: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Default: 5
resolution	string	No	Options: 2kDefault: "2k"
aspect_ratio	string	No	Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16Default: "16:9"
reference_audios	array	No	Optional reference audio URLs. Audio cannot be used alone.
reference_images	array	No	Reference image URLs. Provide at least one image or video reference.
reference_videos	array	No	Reference video URLs. Provide at least one image or video reference.

cURL example

REQUEST_ID=$(curl -s -X POST https://api.muapi.ai/api/v1/minimax-h3-reference-to-video \
  -H "x-api-key: $MUAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"<prompt>"}' | jq -r .request_id)

curl -s https://api.muapi.ai/api/v1/predictions/$REQUEST_ID/result -H "x-api-key: $MUAPI_API_KEY"

Python example

import os, time, requests

API = "https://api.muapi.ai/api/v1"
headers = {"x-api-key": os.environ["MUAPI_API_KEY"]}

r = requests.post(f"{API}/minimax-h3-reference-to-video", headers=headers, json={"prompt":"<prompt>"})
request_id = r.json()["request_id"]

while True:
    res = requests.get(f"{API}/predictions/{request_id}/result", headers=headers).json()
    if res["status"] == "completed":
        print(res["outputs"]); break
    if res["status"] == "failed":
        raise RuntimeError(res.get("error"))
    time.sleep(3)

Full docs and agent/MCP integration: llms.txt. Get an API key at muapi.ai/access-keys.