MiniMax H3 Lite Reference-to-Video generates 480P / 768P videos from reference inputs with flexible 4-15 second duration, making it suitable for character consistency, reference-guided motion, creative videos, social content, ads, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.04per run·~25 / $1
Use the pastry chef from <Image 1> and the red bird from <Image 2>. Preserve his exact identity, hairstyle, chef uniform, and proportions. Preserve the bird’s red feathers, ribbon, size, and markings. The opening frame is a clean medium-wide shot of the chef decorating a cake at the counter, with the red bird perched clearly beside him. The bird suddenly grabs the final strawberry and flies across the counter. The chef quickly reaches after it. The bird drops the strawberry perfectly onto a second unfinished dessert. The chef stops, looks at the unexpectedly perfect result, then looks at the bird in surprise. The camera makes one smooth sideways move following the bird from the first cake to the second dessert. Playful culinary comedy, clear action and payoff, realistic bird movement, expressive reaction, premium food cinematography, clean visual storytelling.
Use the reference for the orange handmade clay submarine and the playful blue octopus. Show them exploring a new underwater garden of tall emerald kelp, glowing purple coral and tiny golden fish. The octopus swims beside the submarine, bubbles rising. Smooth storybook tracking shot, colorful tactile stop-motion animation. Soft marimba melody and underwater bubbles.
Use the reference for the iridescent emerald hummingbird. Show it hovering beside enormous vivid purple and pink flowers in a sunlit botanical glasshouse with warm golden shafts of light and drifting pollen. Close macro view, realistic feather detail, slow graceful camera move. Natural wing flutter and gentle garden ambience.
Use the reference for the small yellow delivery vehicle and rainy futuristic city style. Show it crossing a narrow bridge above a canal surrounded by vivid cyan, magenta and orange neon lights, with steam and rain reflected in the water. Smooth cinematic tracking camera, richly detailed animated night scene. Gentle rainfall, quiet electric motor and distant city ambience.
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 Lite Reference-to-Video generates videos using images, video clips, and optional audio as creative references. Use multimodal inputs to guide characters, objects, environments, motion, and sound while generating 4–15 second videos at 480p or 768p.
9 reference images and 3 reference videos.3 audio clips alongside visual references.4 to 15 seconds.| 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: 480p or 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.480p or 768p.| Resolution | Requested Video | Reference Video |
|---|---|---|
| 480p | $0.025/s | $0.025/s |
| 768p | $0.04/s | $0.04/s |
The first 5 reference images are free. Each additional reference image costs $0.02.
Reference audio does not add a separate charge.
Reference videos are billed with a 2-second minimum per clip and a 15-second combined maximum. Their combined duration is rounded up to the next whole second. The generated video is charged by the requested duration.
480p for lower-cost iteration before moving to 768p.prompt is required.21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Default: 16:9.9 reference images are supported.3 reference videos are supported.3 reference audio clips are supported.2 seconds. The combined processed duration is limited to 15 seconds.2–15 seconds.15 seconds.50 MB.15 MB per file.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/h3-lite/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for H3 Lite Reference To Video below.
set -euo pipefail
: "${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-lite/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-lite/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-lite/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 Lite Reference To Video is a MiniMax model for reference-guided video generation, exposed as a REST API on WaveSpeedAI. MiniMax H3 Lite Reference-to-Video generates 480P / 768P videos from reference inputs with flexible 4-15 second duration, making it suitable for character consistency, reference-guided motion, 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-lite-reference-to-video.
H3 Lite Reference To Video starts at $0.04 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-lite-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.