Model detail
MiniMax H3
MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer. The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation.
Model specs
- Model ID
-
MiniMax-H3
- Context length
- –
- Max output
- –
- I/O modalities
- Released
- 2026-07
02
API endpoints
One MixRoute gateway, OpenAI-compatible
-
OpenAI-compatible
/v1/chat/completionsPOST
03
Tiered pricing
Unit: Varies by price type
| Tier | Per second /second |
|---|---|
2k
res == "2k"
sec * 0.13 + max(in_n - 5, 0) * 0.04
|
$0.1300 |
768p
!(res == "2k")
sec * 0.08 + max(in_n - 5, 0) * 0.04
|
$0.0800 |
05
Selection summary
Quickly judge whether it fits your workload
What is this model good for?
Lightweight, open-weights video generation model from MiniMax
MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering.
What should you check before using it?
Check duration, resolution, and aspect ratio limits
Model type: video. Verify supported features and quotas with the provider documentation. Released 2026-07-30.
Why use it through MixRoute?
MiniMax H3 takes text and images on one route
Text and image inputs share the same route and the same key. MixRoute serves MiniMax H3 on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID MiniMax-H3 and re-run your integration tests.
07
Capabilities & compatibility
Unconfirmed capabilities stay "Unknown," no guesses
Vision input
MiniMax H3 can process image inputs alongside text.
image_url content part alongside text messages.
09
FAQ
MiniMax H3 is a video generation model from MiniMax. It accepts text, image, video, audio and returns video, audio.
One endpoint, a testable decision
Test this model and alternate routes with the same request format
Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.