MiniMax H3 and MiniMax H3 Lite side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
MiniMax Video GenerationMiniMax H3 and MiniMax H3 Lite are both MiniMax models in the Video Generation category, available through the EmpirioLabs API.
| Spec | MiniMax H3 | MiniMax H3 Lite |
|---|---|---|
| Model ID | minimax-h3 | minimax-h3-lite |
| Author | MiniMax | MiniMax |
| Released | Jul 31, 2026 | - |
| Input | Text Image Video Audio | Text Image Video Audio |
| Output | Video | Video |
| Region | Singapore | - |
| Endpoints | POST /v1/videos/generations | POST /v1/videos/generations |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | MiniMax H3 | MiniMax H3 Lite |
|---|---|---|
| prompt | string | string |
| mode | auto, t2v, i2v, flf, r2v, regenerate Default: auto | auto, t2v, i2v, flf, r2v Default: auto |
| resolution | 768p, 2k Default: 768p | 480p, 768p Default: 768p |
| aspect_ratio | adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 Default: adaptive | adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 Default: adaptive |
| duration | 4 to 15 Default: 6 | 4 to 15 Default: 6 |
| image | string | string |
| last_frame | string | string |
| video | string | string |
| audio | string | string |
| base_video | string | - |
| watermark | boolean Default: false | - |
| enhance_prompt | boolean Default: false | - |
MiniMax H3 generates 4 to 15 second clips at 24 fps in 768p or 2K, each with a native stereo audio track.
Set enhance_prompt to true and the model first rewrites your brief into a full prompt, adding shot-by-shot structure, camera moves, lighting and a soundscape, then renders from that. Any reference media you attach informs the expansion. It adds a per-token charge on top of the per-second video cost, and is skipped for regeneration because that path reproduces the original request.
Generates 4 to 15 second clips at 24 fps in 480p or 768p, each with a native stereo audio track.
Image to video and first and last frame follow the input image. Text to video and reference to video use the ratio you choose, or 16:9 when it is left at adaptive.
MiniMax H3 runs through POST /v1/videos/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Both models are called through the same endpoint. Set model to minimax-h3 or minimax-h3-lite. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3",
"prompt": "Describe what you want MiniMax H3 to generate."
}'Prompt tests and comparison runs that cover both models.
MiniMax H3 Lite lists the lower rate for 768p (per second) and Reference image input (per input image after the first 5). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
MiniMax H3 Lite lists the lower rate for 768p (per second) and Reference image input (per input image after the first 5). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/videos/generations with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.
