
Generates 4 to 15 second clips at up to 2K with native stereo audio, following text, image, video, and audio references in one request.
Generates 4 to 15 second clips at up to 2K with native stereo audio, following text, image, video, and audio references in one request.
minimax-h3/v1/videos/generationsminimax/minimax-h3hailuo-3minimax/hailuo-3Live pay-as-you-go rates from the EmpirioLabs catalog. You can also choose a plan with weekly allowances.
MiniMax H3 runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3",
"prompt": "Describe what you want MiniMax H3 to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/videos/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "minimax-h3",
"prompt": "Describe what you want MiniMax H3 to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)Request parameters supported by the MiniMax H3 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| prompt | string | - | - | Scene description, up to 7000 characters. Can describe action, camera work, dialogue, sound effects, and on-screen text. |
| mode | enum | auto | auto, t2v, i2v, flf, r2v, regenerate | auto: detect from the inputs. t2v: text-to-video. i2v: animate one image as the opening frame. flf: transition from a first frame to a last frame. r2v:... |
| resolution | enum | 768p | 768p, 2k | Output resolution. 2K is billed at a higher per-second rate than 768p. |
| aspect_ratio | enum | adaptive | adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Output aspect ratio. Adaptive follows the supplied input media. |
| duration | number | 6 | 4 to 15 | Clip length in seconds, whole numbers only. |
| image | string | - | - | Image URL. One opening frame for image-to-video, or up to 9 reference images for reference-to-video. |
| last_frame | string | - | - | Closing frame image URL. Supplying it selects first and last frame mode. |
| video | string | - | - | Reference video URL, up to 3 clips of 2 to 15 seconds each. Reference video is billed for its own duration in addition to the generated clip. |
| audio | string | - | - | Reference audio URL, up to 3 clips of 2 to 15 seconds each. Requires an accompanying reference image or video. |
| base_video | string | - | - | A 768p clip previously generated by this model, to re-render at 2K. Supplying it selects regeneration, which is billed at its own lower per-second rate on the source... |
| watermark | boolean | false | - | Add the AI-generated content watermark to the output. |
| enhance_prompt | boolean | false | - | Expand your brief into a full prompt before rendering, adding shot structure, camera work and a soundscape. Any reference media you attach informs the expansion.... |
MiniMax H3 generates 4 to 15 second clips at 24 fps in 768p or 2K, each with a native stereo audio track.
Set enhance_prompt to true and the model first rewrites your brief into a full prompt, adding shot-by-shot structure, camera moves, lighting and a soundscape, then renders from that. Any reference media you attach informs the expansion. It adds a per-token charge on top of the per-second video cost, and is skipped for regeneration because that path reproduces the original request.
Announcements, prompt tests, and comparisons that cover this model.
API Access How to Use the MiniMax H3 API MiniMax H3 is available on EmpirioLabs: 4 to 15 second clips at up to 2K with a native stereo audio track, from text,...
Guides Seedance 2.5 vs MiniMax H3 vs Grok Imagine Video 1.5 vs HappyHorse 1.1: image to video test Seedance 2.5, MiniMax H3, Grok Imagine Video 1.5 and HappyHorse 1.1 all animated the same vertical starting image across...
Guides Seedance 2.5 vs Kling 3.0 Turbo vs MiniMax H3 vs Wan 3.0: image to video test Seedance 2.5, Kling 3.0 Turbo, MiniMax H3 and Wan 3.0 all animated the same vertical starting image across three scenes,...On EmpirioLabs, MiniMax H3 is billed pay as you go: 768p $0.18 per second; 2K $0.26 per second; 2K regeneration $0.10 per second; Reference image input $0.08 per input image after the first 5; Prompt expansion input $1.80 per 1M prompt tokens; Prompt expansion output $7.20 per 1M generated tokens. You can also choose a plan with weekly allowances. The live rate card on this page always matches what the API charges.
MiniMax H3 takes Text, Image, Video, Audio as input and returns Video.
MiniMax H3 supports 768p, 2K. The default is 768p, and the parameter reference lists any limits by resolution.
MiniMax H3 is served through POST /v1/videos/generations on api.empiriolabs.ai with standard bearer-token authentication.
Send minimax-h3 as the model in your request. The alternate IDs minimax/minimax-h3, hailuo-3, minimax/hailuo-3 also work.
MiniMax released MiniMax H3 on Jul 31, 2026.
MiniMax H3 on EmpirioLabs is served from Singapore.
Yes. The EmpirioLabs playground runs MiniMax H3 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make. You can also choose a plan with weekly allowances.
Check out our pricing or reach out if you want your own model deployed on our stack.