Minimax H3 Text To Video API Documentation
Playground
Try it on WaveSpeedAI!MiniMax H3 Text to Video generates coherent 2K videos from text prompts, with flexible 5-15 second duration and adaptive or custom aspect ratios for cinematic scenes, creative videos, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
MiniMax H3 Text-to-Video generates high-resolution videos from text prompts. Describe the video scene, action, camera movement, and visual style, then choose aspect ratio and duration to create a 2k video output.
Why Choose This?
-
Text-to-video generation
Generate videos directly from natural-language prompts. -
2K video output
Create high-resolution video outputs with the fixed2kresolution tier. -
Flexible aspect ratios
Supports wide, landscape, square, portrait, and vertical formats including21:9,16:9,4:3,1:1,3:4, and9:16. -
Selectable duration
Generate videos from4to15seconds. -
Simple generation workflow
Provide a prompt, choose aspect ratio and duration, then generate the final video.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video scene, action, camera movement, and style. Minimum length: 1 character. |
| 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 values: 768p or 2k. |
| duration | No | Output video duration in seconds. Supported values: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, or 15. |
How to Use
- Write your prompt — Describe the scene, subject, action, camera movement, lighting, mood, and visual style.
- Choose aspect ratio — Select the layout that matches your target format.
- Set duration — Choose a video length from
4to15seconds. - Submit — Generate the video and retrieve the output URL.
Pricing
Pricing is based on output resolution and generated video duration.
| Resolution | Per second | 5s | 10s | 15s |
|---|---|---|---|---|
| 768p | $0.10 | $0.50 | $1.00 | $1.50 |
| 2K | $0.14 | $0.70 | $1.40 | $2.10 |
Best Use Cases
- Cinematic video generation — Create high-resolution video scenes from detailed text prompts.
- Marketing and campaign videos — Generate polished video concepts for ads, brand visuals, and promotional content.
- Social media content — Produce landscape, square, or vertical videos for different platforms.
- Story and scene prototyping — Turn written ideas into short motion clips for creative planning.
- Visual concept development — Explore camera movement, action, lighting, and mood before production.
Pro Tips
- Use detailed prompts with subject, action, camera movement, lighting, style, and mood.
- Choose
16:9for widescreen video,9:16for vertical mobile content, and1:1for square layouts. - Use
21:9for cinematic wide-frame scenes. - Use shorter durations for quick prompt testing and longer durations when the scene needs more time to develop.
- Keep the prompt focused on visible motion and scene progression.
Related Models
- MiniMax H3 Image-to-Video — Generate high-resolution video from a first-frame image and prompt.
- MiniMax H3 Reference-to-Video — Generate high-resolution video from reference media and prompt guidance.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"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/text-to-video" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text description of the video scene, action, camera movement, and style. | |
| aspect_ratio | string | No | 16:9 | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Output aspect ratio. Adaptive selects a suitable ratio automatically. |
| resolution | string | No | 768p | 768p, 2k | Output video resolution. |
| duration | integer | No | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Output video duration in seconds. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |