MiniMax H3
Native 2K video with stereo audio from text, a first and optional last frame, or image and audio references. Use it for expressive motion, legible in-frame text, and multimodal scenes up to 15 seconds.
Cost
from 3 tokens/s
Try MiniMax H3 in Givon AI
Open a working project for regular creation, or use Playground to inspect the model parameters.
Use through API
Request fields, constraints, and ready-to-use examples for developers. The user workflow starts above.
IDEMPOTENCY_KEY="${IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.givon.ai/api/v1/generations \
-H "Authorization: Bearer $GIVON_API_KEY" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"type":"video","model":"minimax-h3","input":{"prompt":"cinematic drone shot over a city at night","aspectRatio":"9:16","resolution":"2k","duration":5,"audioEnabled":true,"referenceAssetUris":["asset://asset_..."]}}'Input fields
* required| Field | Type | Default | Allowed |
|---|---|---|---|
prompt* promptGeneration prompt describing the scene, action and direction. | string | — | up to 7000 chars |
aspectRatio aspectRatio | string | 9:16 | 16:9, 1:1, 21:9, 3:4, 4:3, 9:16 |
resolution resolution | string | 2k | 768p, 2k |
duration duration | number | 5 | 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 |
audioEnabled audioEnabledAudio is created automatically and cannot be turned off separately. | boolean | true | boolean |
Start image startImageAsset input for the startImage slot. | string | — | image · asset, https, data |
End image endImageAsset input for the endImage slot. | string | — | image · asset, https, data |
Speech audio speechAudioAsset input for the speechAudio slot. | string | — | voiceover · asset, https, data |
Speech audio 2 speechAudio2Asset input for the speechAudio2 slot. | string | — | voiceover · asset, https, data |
Speech audio 3 speechAudio3Asset input for the speechAudio3 slot. | string | — | voiceover · asset, https, data |
Reference images referenceAssetUrisOptional reference assets as asset:// URIs, HTTPS URLs, or data URIs. | array | — | image · up to 9 · asset, https, data |
promptGeneration prompt describing the scene, action and direction.
- Type
- string
- Default
- —
- Allowed
- up to 7000 chars
aspectRatio- Type
- string
- Default
- 9:16
- Allowed
- 16:9, 1:1, 21:9, 3:4, 4:3, 9:16
resolution- Type
- string
- Default
- 2k
- Allowed
- 768p, 2k
duration- Type
- number
- Default
- 5
- Allowed
- 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
audioEnabledAudio is created automatically and cannot be turned off separately.
- Type
- boolean
- Default
- true
- Allowed
- boolean
startImageAsset input for the startImage slot.
- Type
- string
- Default
- —
- Allowed
- image · asset, https, data
endImageAsset input for the endImage slot.
- Type
- string
- Default
- —
- Allowed
- image · asset, https, data
speechAudioAsset input for the speechAudio slot.
- Type
- string
- Default
- —
- Allowed
- voiceover · asset, https, data
speechAudio2Asset input for the speechAudio2 slot.
- Type
- string
- Default
- —
- Allowed
- voiceover · asset, https, data
speechAudio3Asset input for the speechAudio3 slot.
- Type
- string
- Default
- —
- Allowed
- voiceover · asset, https, data
referenceAssetUrisOptional reference assets as asset:// URIs, HTTPS URLs, or data URIs.
- Type
- array
- Default
- —
- Allowed
- image · up to 9 · asset, https, data
Cost
from 3 tokens/sThe variant is selected automatically from request fields, so you do not need to send it.
Capabilities
text_to_videotext_image_to_videoimage_to_videostartImage:imageendImage:imagespeechAudio:voiceoverspeechAudio2:voiceoverspeechAudio3:voiceoverreferenceAssetUris:image[]<=9