curl --request POST \
--url https://api.omniall.ai/v1/videos/h3_context_ir \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "MiniMax-H3",
"prompt": "A cat running on grass in bright sunlight",
"duration": 5,
"resolution": "2K",
"ratio": "16:9"
}
'{
"id": "<string>",
"task_id": "<string>",
"status": "<string>",
"object": "<string>"
}H3 Context IR create
MiniMax-H3 Context IR enhanced create.
Path: POST https://api.omniall.ai/v1/videos/h3_context_ir
Deep multimodal reasoning. Same fields as create; or set context_ir_enabled: true on POST /v1/videos.
Mutual exclusion: first_frame / last_frame (incl. image, images[0], first_frame_url) cannot mix with reference_images / reference_videos / reference_audios (or content reference_*).
Equivalents: first_frame_url ≈ first_frame ≈ image ≈ images[0].
ratio rules:
- t2va: text-only →
ratiorequired, notadaptive - i2va: with first/last frame →
ratioforced toadaptive - r2va: with
reference_*→ratiooptional (defaultadaptive)
curl --request POST \
--url https://api.omniall.ai/v1/videos/h3_context_ir \
--header 'Authorization: <authorization>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "MiniMax-H3",
"prompt": "A cat running on grass in bright sunlight",
"duration": 5,
"resolution": "2K",
"ratio": "16:9"
}
'{
"id": "<string>",
"task_id": "<string>",
"status": "<string>",
"object": "<string>"
}Headers
Bearer API key, e.g. Bearer sk-....
"Bearer sk-..."
Body
MiniMax-H3 create-video body.
Model id: MiniMax-H3.
"MiniMax-H3"
Text prompt (or content text).
"A cat running on grass in bright sunlight"
Seconds, 4–30. Alias: seconds.
4 <= x <= 305
Aspect ratio. t2va required (not adaptive); i2va forced adaptive; r2va optional.
adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 "16:9"
480P / 768P / 1080P / 2K.
480P, 768P, 1080P, 2K "2K"
Single first-frame URL (equiv. first_frame).
Enable Context IR. Or use /v1/videos/h3_context_ir.
Show child attributes
Show child attributes