Hailuo 2.3 API
MiniMax Hailuo 2.3 — physics-aware text-to-video and image-to-video with 2.5× efficiency improvement and 85% complex-instruction accuracy. Standard and Pro tiers at 768p and 1080p, plus Fast variants optimized for creators and marketers.
Text-to-video at Standard (768p) and Pro (1080p) tiers. Image-to-video at i2v-standard, i2v-pro, fast, and fast-pro variants. Fast tier generates 6s and 10s clips at 768p; Fast Pro delivers 6s 1080p output.
About the Hailuo 2.3 API
What Hailuo 2.3 does, how it fits in the MiniMax model lineup, and why teams reach for it.
Hailuo 2.3 is a video generation model from MiniMax, available through the WaveSpeedAI REST API. MiniMax Hailuo 2.3 — physics-aware text-to-video and image-to-video with 2.5× efficiency improvement and 85% complex-instruction accuracy. Standard and Pro tiers at 768p and 1080p, plus Fast variants optimized for creators and marketers.
Text-to-video at Standard (768p) and Pro (1080p) tiers. Image-to-video at i2v-standard, i2v-pro, fast, and fast-pro variants. Fast tier generates 6s and 10s clips at 768p; Fast Pro delivers 6s 1080p output.
The Hailuo 2.3 family on WaveSpeedAI ships 6 REST endpoints covering Image-To-Video, Text-To-Video workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Hailuo 2.3 through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Hailuo 2.3 API endpoints
6 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.
Fast Pro
Hailuo 2.3 Fast Pro converts images into high-quality 6s 1080p videos, delivering fast, affordable results for creators and marketers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Fast
Hailuo 2.3 Fast by minimax generates high-quality 6s and 10s image-to-video clips at 768p, optimized for creators and marketers. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
I2v Pro
MiniMax Hailuo 2.3 Pro is an image-to-video model for ultra-clear 1080P output and physics-aware scenes with responsive rendering. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
I2v Standard
MiniMax Hailuo 2.3 Standard is an image-to-video model producing physics-aware 768p output with a 2.5x efficiency improvement. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
T2v Standard
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.
T2v Pro
MiniMax Hailuo 2.3 Pro is a text-to-video model delivering 1080p videos with 2.5x efficiency and 85% complex-instruction accuracy. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
See Hailuo 2.3 in action
Real outputs generated by the Hailuo 2.3 API. Hover any video to preview, click to open the full-size viewer.
How to use the Hailuo 2.3 API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-standard. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from"queued" or"processing" to"completed".
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Hailuo 2.3 variant you called.
What you can build with Hailuo 2.3
Common workflows developers and creators use the Hailuo 2.3 API for.
Physics-aware text-to-video at 768p
minimax/hailuo-2.3/t2v-standard creates physics-aware 768p videos with 2.5× efficiency and 85% complex-instruction response rate — the Standard tier for prompt-driven video from text.
Pro text-to-video at 1080p
minimax/hailuo-2.3/t2v-pro delivers 1080p videos with 2.5× efficiency and 85% complex-instruction accuracy — the Pro tier when delivery resolution and instruction-following matter most.
Image-to-video with physics-aware scenes
minimax/hailuo-2.3/i2v-standard and i2v-pro convert images into physics-aware videos at 768p and 1080p respectively — responsive rendering for complex physics-driven scenes per the catalog.
Fast tier for 6s and 10s clips
minimax/hailuo-2.3/fast generates high-quality 6s and 10s image-to-video clips at 768p, optimized for creators and marketers — useful for social content where short duration and fast turnaround matter.
Fast Pro for 1080p speed
minimax/hailuo-2.3/fast-pro converts images into high-quality 6s 1080p videos with fast, affordable results — the speed-optimized 1080p tier for creator workflows.
Complex instruction following
Catalog claim: 85% complex-instruction accuracy across text-to-video variants. Write multi-clause prompts with subject, action, environment, and camera language — Hailuo 2.3 is tuned for instruction-heavy briefs.
Tips for prompting Hailuo 2.3
Practical advice for getting better outputs from Hailuo 2.3 — drawn from the patterns that work across video models in production pipelines.
Write complex multi-clause prompts
Catalog claim: 85% complex-instruction accuracy. Hailuo 2.3 is tuned for instruction-heavy briefs — subject, action, environment, camera, and style in one prompt.
Pick Standard vs Pro by resolution
t2v-standard and i2v-standard at 768p for iteration; t2v-pro and i2v-pro at 1080p for delivery. Same prompt format across tiers.
Physics-aware scenes need explicit motion
Catalog emphasizes physics-aware rendering. Describe object interactions, gravity, and material behavior — not just static scene descriptions.
Image-to-video for product and lifestyle
i2v variants animate product photos and lifestyle stills with responsive physics-aware rendering — useful for e-commerce and ad creative from existing photography.
Hailuo 2.3 API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| minimax/hailuo-2.3/fast-pro | image-to-video | $0.33 |
| minimax/hailuo-2.3/fast | image-to-video | $0.19 |
| minimax/hailuo-2.3/i2v-pro | image-to-video | $0.49 |
| minimax/hailuo-2.3/i2v-standard | image-to-video | $0.28 |
| minimax/hailuo-2.3/t2v-standard | text-to-video | $0.28 |
| minimax/hailuo-2.3/t2v-pro | text-to-video | $0.49 |
Call the Hailuo 2.3 API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-standard" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("minimax/hailuo-2.3/t2v-standard", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"minimax/hailuo-2.3/t2v-standard",
{}
)
print(output["outputs"][0]) # → URL of the generated outputHailuo 2.3 vs alternatives
When to pick Hailuo 2.3 over similar models on WaveSpeedAI.
Hailuo 2.3 vs Hailuo 02
Hailuo 02 is the prior generation with similar Standard/Pro/Fast tier structure at comparable resolutions. Hailuo 2.3 adds the 2.5× efficiency claim and 85% complex-instruction accuracy as headline improvements.
Hailuo 2.3 vs Seedance 1.5 Pro
Seedance 1.5 Pro ships Smart Duration, seeds, video-extend, and optional audio at a lower price point. Hailuo 2.3 emphasizes physics-aware rendering and complex-instruction accuracy with dedicated Fast tiers for creator workflows.
Hailuo 2.3 vs Wan 2.6
Wan 2.6 ships synced audio, reference-to-video, video-extend, and image-edit in the same family. Hailuo 2.3 stays focused on text-to-video and image-to-video with physics-aware rendering and Fast tiers for short-form content.
Hailuo 2.3 API — Frequently asked questions
Pricing, license, integration — common questions about running Hailuo 2.3 on WaveSpeedAI.
What is the Hailuo 2.3 API?
Hailuo 2.3 is a MiniMax video generation model exposed as a REST API on WaveSpeedAI. MiniMax Hailuo 2.3 — physics-aware text-to-video and image-to-video with 2.5× efficiency improvement and 85% complex-instruction accuracy. Standard and Pro tiers at 768p and 1080p, plus Fast variants optimized for creators and marketers. You can call it programmatically or try it from the playground linked above.
How do I call the Hailuo 2.3 API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/minimax/hailuo-2.3/t2v-standard with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to "completed", then read the output URL from data.outputs[0]. Full Python / Node.js / cURL examples are above.
How much does the Hailuo 2.3 API cost?
Hailuo 2.3 starts at $0.19 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Hailuo 2.3 variants are available?
WaveSpeedAI hosts 6 Hailuo 2.3 endpoints: minimax/hailuo-2.3/fast-pro, minimax/hailuo-2.3/fast, minimax/hailuo-2.3/i2v-pro, minimax/hailuo-2.3/i2v-standard, minimax/hailuo-2.3/t2v-standard, minimax/hailuo-2.3/t2v-pro. Each variant has its own playground page and pricing.
Can I use Hailuo 2.3 outputs commercially?
Commercial usage rights follow the MiniMax model license. Most MiniMax models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Hailuo 2.3 on WaveSpeedAI instead of going direct?
One API key + one billing account across Hailuo 2.3 AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below MiniMax's direct API.
About MiniMax
The team behind Hailuo 2.3 and the broader MiniMax model lineup on WaveSpeedAI.
MiniMax is a Chinese AI lab known for Hailuo video generation and speech models. Hailuo 2.3 ships physics-aware text-to-video and image-to-video with Standard, Pro, and Fast tiers — positioned around 2.5× efficiency and strong complex-instruction accuracy for creator and marketing workflows.
Start building with Hailuo 2.3 on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from MiniMax and every other provider.