model apis · video generation
Run Minimax H3 by MiniMax through one OpenAI-compatible endpoint. Pay per use against your deeprelay balance. No instance to rent, no deployment to manage.
Available nowLive catalog rates, billed per use against your deeprelay balance, no minimums. Minimax H3 is priced per use rather than included in the $2.99-a-month flat plan.
| Tier | Rate |
|---|---|
| Serverless | Per second of video: $0.147Per clip (from): $0.737 |
rates are read every few minutes from the live model catalog and metered per request
Any OpenAI SDK works: set the base URL to https://api.deeprelay.ai/v1 and use your deeprelay API key.
# Start a generation, then poll it until it completes.
curl https://api.deeprelay.ai/v1/videos \
-H "Authorization: Bearer $DEEPRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deeprelay/minimax-h3",
"prompt": "A drone shot over a mountain lake at dawn"
}'
curl https://api.deeprelay.ai/v1/videos/{video_id} \
-H "Authorization: Bearer $DEEPRELAY_API_KEY"| Model id | deeprelay/minimax-h3 |
| Modality | Video generation |
| Author | MiniMax |
| Context window | – |
| Streaming | – |
| Aliases | – |
| Flat plan | Not included: pay as you go |
faq
Minimax H3 on deeprelay currently costs $0.147 (per second of video), $0.737 (per clip (from)), billed against your deeprelay balance as you go. There are no minimums. It is priced per use rather than included in the $2.99-a-month flat plan, which covers a named set of models.
Yes. Point any OpenAI SDK at https://api.deeprelay.ai/v1 with a deeprelay API key and request model "deeprelay/minimax-h3". No proprietary client needed.
Generation models bill per output (per image, or per second of video) at the listed rate, metered per request against your deeprelay balance.