Build next-gen apps with MiniMax H3
Pricing
Official Price
TokenLab Price
One-click test
Sign in once and Web Agent keeps this model, prompt, and request preset for you.
Test hailuo-h3 in Web Agent. Run the recommended text-to-video request at /v1/videos/generations, then show request body, task id, poll URL or final status.
API workbench
The default route for production. The code sample below uses this endpoint with the format you pick.
curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
-H "Authorization: Bearer sk-xxx" \
-H "Content-Type: application/json" \
-d '{
"duration": 6,
"operation": "text-to-video",
"resolution": "768p",
"aspect_ratio": "16:9",
"model": "hailuo-h3",
"prompt": "Cinematic sunrise over a calm lake with gentle camera motion."
}'Use cases
Best forMultimodal
Tasks that mix text, images, audio, or video in one request
Text to Video
Generating short videos and iterating on creative cuts
Storyboard tests
Create motion concepts with visible task status and final asset handling.
Social clips
Prototype short launch videos, product shots, and campaign cuts in minutes.
Async flow check
Create, poll, and inspect completed video tasks with the same API pattern.
Side-by-side test
Compare real response quality, latency, and price for production defaults.
Prompt examples
Generate an 8-second cinematic product reveal with a slow camera push.
Storyboard a social clip for a new AI API feature.
Run image-to-video from this product shot and walk me through the task status flow.
FAQ
How much does MiniMax H3 cost?
On TokenLab, MiniMax H3 costs $0.08-$0.13 Per Second. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What is MiniMax H3 best for?
MiniMax H3 is a strong fit for Image to Video, Multimodal, Reference to Video. You can call it through TokenLab with one API key.
How do I call the MiniMax H3 API?
Get a TokenLab API key, then send your request to https://api.tokenlab.sh/v1/videos/generations. The API workbench above has a recommended endpoint and copy-ready code.
Which endpoint should MiniMax H3 use?
Use https://api.tokenlab.sh/v1/videos/generations as the default for MiniMax H3. If a provider-native format is supported, the API workbench shows that endpoint too.
Can I test MiniMax H3 before integrating it?
Yes. Try in Web Agent opens a ready test for MiniMax H3 and keeps your prompt after sign-in, so you don’t lose context.
Which operations does MiniMax H3 support?
MiniMax H3 supports Image to Video, Reference to Video, Start-End to Video, Text to Video. Pick an operation in the API workbench above to see the matching endpoint and code sample.
