Minimax Hailuo 2.3 T2V Standard
Playground
Try it on WaveSpeedAI!Hailuo 2.3 is a text-to-video model creating physics-aware 768p videos with 2.5× efficiency and 85% complex instruction response rate. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Hailuo 2.3 Standard is the latest generation of AI video creation models, featuring advanced physics rendering and cinematic-grade scene transitions. Built for both creators and professionals, it combines high fidelity, reliability, and cost efficiency, outperforming many closed or premium video generation systems.
🎬 Why It Looks Great
- Flexible Duration Options — Generate 6-second or 10-second cinematic clips.
- Realistic Motion & Physics — Handles complex dynamics such as water flow, debris movement, and camera shake with physical consistency.
- Seamless Scene Transitions — Produces smooth, natural visual transitions without abrupt cuts.
- Reliable Consistency — Reproducible results across identical prompts for precise creative control.
- Professional Quality, Affordable Price — Achieve production-level results at a fraction of competitors’ cost.
⚙️ Limits and Performance
- Output resolution: fixed at 768p
- Maximum clip length per job: 10 seconds
- Duration options: 6 s or 10 s
- Processing time: approximately 30 – 90 seconds per clip (depending on scene complexity and queue load)
💰 Pricing
| Duration | Cost per Job | Max Resolution |
|---|---|---|
| 6 seconds | $0.23 | 768p |
| 10 seconds | $0.56 | 768p |
🧾 Billing Rules
- Flat-rate billing per clip (6 s or 10 s).
- No prorated pricing — shorter clips are charged at the full duration tier.
- Total cost = number of clips × rate.
🚀 How to Use
- Write a prompt describing the desired scene, lighting, motion, or camera movement.
- Choose your duration (6 s or 10 s).
- Submit the job and wait for processing.
- Download your completed video once ready.
🎥 Pro Tips for Best Quality
- Craft cinematic prompts that specify camera angles, lighting style, and mood.
- Use dynamic verbs (e.g., zoom in, pan left, fly over) to introduce camera motion.
- Start with 6-second drafts to experiment quickly before producing longer versions.
- Combine multiple short clips to create narrative sequences.
- Pair your visuals with music or voiceovers for full storytelling impact.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"duration": 6,
"enable_prompt_expansion": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-standard" \
-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 | - | The positive prompt for the generation. | |
| duration | integer | No | 6 | 6, 10 | The duration of the generated media in seconds. |
| enable_prompt_expansion | boolean | No | true | - | The model automatically optimizes incoming prompts to enhance output quality. This also activates the safety checker, which ensures content safety by detecting and filtering potential risks. |
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 |