Minimax Hailuo 2.3 T2V Standard
Playground
Try it on WavespeedAI!Hailuo 2.3 Standard - MiniMax’s next-generation AI video model ranked #2 globally. Features 2.5x efficiency improvement, 85% complex instruction response rate, and extreme physics simulation capabilities for high-quality 768p video generation.
Features
Hailuo 2.3 Standard
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 1080p
- 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 | 1080p |
| 10 seconds | $0.56 | 1080p |
🧾 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
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-standard" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"duration": 6,
"enable_prompt_expansion": true
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
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 | Array of URLs to the generated content (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.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| 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 |