MiniMax H3 text-to-video: turn a single prompt into cinematic AI video with no reference images. It understands natural-language descriptions of characters, scenes, motion, camera work and lighting, producing smooth, temporally consistent footage. Supports 1–15 second clips in 736p portrait, landscape or 1:1, billed per second. Ideal for short films, brand marketing, product showcases, social content and previsualization.
curl 'https://api.chinesemodels.ai/v1/chat/completions' \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax_h3_b99_001",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Prices are per 1M tokens unless the model is billed per call. Final cost depends on the tokens actually processed by the upstream provider.