Video model API
MiniMax H3 Max Turbo API
MiniMax H3 Max Turbo is a high-throughput image-to-video model from MiniMax, post-trained for stronger prompt adherence and improved visual aesthetics. It is co-optimized with fal’s inference stack to deliver faster generation while maintaining output quality. The model can animate a supplied image as the first frame, use an end frame to guide the destination state, or use both for more controlled transitions. It supports 480p, 768p, and 1080p generation, with configurable video duration and prompt expansion modes.
- Model id
minimax-h3-max-turbo- Takes
- Text (required)
- Makes
- Video
- Endpoint
POST /api/v1/run- Made by
- MiniMax
- Mode
- Synchronous
Call MiniMax H3 Max Turbo
https://payload.rentprompts.com/api/v1. Replace the placeholder with your key.Model minimax-h3-max-turbo
POST /api/v1/runasync · poll /v1/jobs/:id
curl https://payload.rentprompts.com/api/v1/run \
-H "Authorization: Bearer rp_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3-max-turbo",
"prompt": "A slow drone shot over a misty pine forest"
}'
# Async models answer HTTP 202 with a job. Poll it until status is
# "succeeded" (output.url / output.urls) or "failed" (error):
curl https://payload.rentprompts.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer rp_live_YOUR_KEY"Replace rp_live_YOUR_KEY with your key, ideally via the RENTPROMPTS_API_KEY environment variable. Keys are shown only once, so they are never filled in here. Get your API key →
What a typical call costs
- 5 seconds of output25 Joules
- 10 seconds of output50 Joules
Send requests to POST /api/v1/run. MiniMax H3 Max Turbo answers synchronously: the result comes back in the response to the same request.