MiniMax H3 Highspeed Reference-to-Video generates fast 768P videos from multimodal references with flexible 4-15 second duration, making it suitable for reference-guided character consistency, motion control, creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.06per run·~16 / $1
Use the pilot from <Image 1> and the mechanical butterfly from <Image 2>. Preserve her exact face, hairstyle, flight suit, helmet, and proportions. Preserve the butterfly’s silver body, translucent cyan wings, circuitry, and glowing core. The opening frame is a clean medium shot of the pilot standing beside an aircraft cockpit, with the mechanical butterfly resting clearly on her glove. The butterfly suddenly opens its wings and flies toward the aircraft. It lands on a damaged control panel. The panel instantly powers back on. The pilot looks from the glowing controls to the butterfly with surprised recognition. The camera makes one smooth follow from her hand to the cockpit panel. Grounded science-fiction, elegant mechanical detail, clear visual payoff, cinematic aviation lighting.
Use the reference for the little red paper fox and handcrafted layered-paper style. Create a new twilight woodland scene with indigo paper trees, glowing turquoise mushrooms and warm golden fireflies. The fox walks across a tiny paper bridge over a blue stream. Smooth slow camera move, colorful storybook cut-paper animation. Gentle woodwind music and soft water sounds.
Use the reference island and pastel village as the main subject. Show this miniature floating island in a dreamy turquoise night sky under a large golden crescent moon, with glowing cottage windows, luminous waterfalls and small colorful balloons passing by. Slow gentle orbit, whimsical polished 3D animation. Soft celesta music, flowing water and wind.
Use the reference for the sparkling citrus drink and realistic glass details. Create a premium macro drink advertisement on a warm coral-pink studio background with slices of orange and fresh mint. Slowly orbit the glass as effervescent bubbles rise and a few water droplets slide down the outside. Bright fresh lighting, orange and pink palette. Crisp fizzing and light ice clinks.
Use the reference image for the dancer and amber dress. Show a graceful slow turn in a bright sunlit studio, flowing fabric, one continuous cinematic shot. Soft piano music and quiet footsteps.
MiniMax H3 Highspeed Reference-to-Video generates videos from multimodal references, including images, video clips, and audio. Use references to guide characters, objects, environments, motion, and sound while generating 4–15 second videos at 768p.
9 reference images and 3 reference videos.3 audio clips alongside visual references.4 to 15 seconds.768p.| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the desired scene, action, camera movement, and how the references should be used. Supports 1–7000 characters. |
| reference_images | Conditional | Up to 9 reference images. At least one image or video reference is required. |
| reference_videos | Conditional | Up to 3 reference video clips. Clips are adjusted to 2–15 seconds each and no more than 15 seconds combined. |
| reference_audios | No | Up to 3 reference audio clips. Each clip must be 2–15 seconds, with a combined duration of up to 15 seconds. Audio cannot be used without an image or video reference. |
| aspect_ratio | No | Output aspect ratio: 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Default: 16:9. |
| resolution | No | Output resolution: 768p. Default: 768p. |
| duration | No | Output video duration in whole seconds from 4 to 15. Default: 5. |
At least one reference image or reference video must be provided. Audio-only requests are not supported.
4 to 15 seconds.| Item | Price |
|---|---|
| Requested video | $0.06/s |
| Reference video | $0.06/s |
| First 5 reference images | Free |
| Each additional reference image | $0.03 |
| Reference audio | Free |
Reference videos are billed with a 2-second minimum per clip and a 15-second combined maximum. Their combined duration is rounded up to the next whole second. The generated video is charged by the requested duration.
prompt is required.21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Default: 16:9.9 reference images are supported.3 reference videos are supported.3 reference audio clips are supported.2 seconds. The combined processed duration is limited to 15 seconds.2–15 seconds.15 seconds.50 MB.15 MB per file.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/h3-highspeed/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for H3 Highspeed Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/minimax/h3-highspeed/reference-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/minimax/h3-highspeed/reference-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "16:9",
"resolution": "768p",
"duration": 5
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/minimax/h3-highspeed/reference-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)H3 Highspeed Reference To Video is a MiniMax model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. MiniMax H3 Highspeed Reference-to-Video generates fast 768P videos from multimodal references with flexible 4-15 second duration, making it suitable for reference-guided character consistency, motion control, creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-h3-highspeed-reference-to-video.
H3 Highspeed Reference To Video starts at $0.06 per run or per second. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `reference_images`, `reference_audios`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/minimax/minimax-h3-highspeed-reference-to-video.
Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.
Commercial usage rights depend on the model's license, set by its provider (MiniMax). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.