MiniMax H3 Reference to Video generates coherent 2K videos from natural-language prompts and multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
निष्क्रिय
$0.13प्रति रन·~76 / $10
A lone female traveler in desert robes standing before the enormous half-buried remains of a giant ancient machine in a vast desert, blowing sand, dramatic sky, epic scale, cinematic science fantasy, strong composition, detailed textures. Sand blows across the ruins as the traveler walks forward slowly. Small lights begin flickering inside the ancient machine, dust falls from its metal surface, and the camera rises upward to reveal the full colossal scale of the buried structure.
MiniMax H3 Reference-to-Video generates high-resolution videos from a text prompt and reference media. Provide at least one reference image or video, optionally add reference audio, then describe the desired scene, interaction, camera movement, and visual style to create a 2k video output.
Reference-guided video generation
Generate videos using reference images or videos to guide the final result.
Image and video reference support
Use reference images for visual style, characters, objects, or scene composition, and reference videos for motion or interaction guidance.
Optional reference audio
Add reference audio when audio guidance is needed, together with image or video references.
2K video output
Create high-resolution video outputs with the fixed 2k resolution tier.
Flexible aspect ratios
Supports wide, landscape, square, portrait, and vertical formats including 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16.
Selectable duration
Generate videos from 5 to 15 seconds.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired video scene and interactions. Minimum length: 1 character. Maximum length: 4000 characters. |
| reference_images | No | Reference image URLs. Supports up to 9 images. At least one reference image or video is required. |
| reference_videos | No | Reference video URLs. Supports up to 3 videos. At least one reference image or video is required. |
| reference_audios | No | Optional reference audio URLs. Supports up to 3 audio files. Audio cannot be provided alone. |
| aspect_ratio | No | Output aspect ratio: 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. |
| resolution | No | Output video resolution. Supported value: 2k. |
| duration | No | Output video duration in seconds. Supported values: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, or 15. |
5 to 15 seconds.Generated 2K video costs $0.13 per output second.
| Output Duration | Output Price |
|---|---|
| 5s | $0.65 |
| 10s | $1.30 |
| 15s | $1.95 |
16:9 for widescreen video, 9:16 for vertical mobile content, and 1:1 for square layouts.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/minimax/h3/reference-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for H3 Reference To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "21:9",
"resolution": "2k",
"duration": 5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/minimax/h3/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=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/minimax/h3/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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"aspect_ratio": "21:9",
"resolution": "2k",
"duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${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"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
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": "21:9",
"resolution": "2k",
"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/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 = task.get("urls", {}).get("get") or 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"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)H3 Reference To Video is a MiniMax model for video generation from images, exposed as a REST API on WaveSpeedAI. MiniMax H3 Reference to Video generates coherent 2K videos from natural-language prompts and multimodal references, including images, videos, and audio, guiding subject consistency, motion, timing, visual style, and scene continuity. 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 production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/minimax/minimax-h3-reference-to-video.
H3 Reference To Video starts at $0.13 per run. 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-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). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.