Create video

Submit MiniMax-H3 official-format multimodal video generation tasks, with support for H3-Context-IR prompt enhancement and video remix.

POST /v2/video_generation

Available models

Headers

Name	Type	Required	Description
	string	Yes	Request authentication. Use a Bearer Token, for example: .
	string	Yes	Content type. Must be .

Request body

Name	Type	Required	Description
	string	Yes	Model name. See Available models above.
	array<object>	No	Multimodal input array. Order affects role assignment. See child fields below.
	string	Yes	Content type: , , , .
	string	No	Required when . Prompt text.
	object	No	Used when . Must include : public image URL. Supports JPG, JPEG, PNG, WEBP, HEIC, HEIF; max 30 MB per file; width/height 256–5760 px; aspect ratio 0.4–2.5. First frame ≤ 1, last frame ≤ 1, reference images ≤ 9.
	object	No	Used when . Must include : public reference video URL. Supports MP4, MOV with H.264/AVC or H.265/HEVC; max 50 MB per file; count ≤ 3; each clip 2–15 s, total duration ≤ 15 s; width/height 256–5760 px; aspect ratio 0.4–2.5; frame rate 23.976–60.
	object	No	Used when . Must include : public reference audio URL. Supports WAV, MP3; max 15 MB per file; count ≤ 3; each clip 2–15 s, total duration ≤ 15 s.
	string	No	Media role: - : first frame (image) - : last frame (image) - : reference image - : reference video - : reference audio
	integer	Yes	Target video duration in seconds, range .
	string	No	Video aspect ratio: , , , , , , .
	string	No	Callback URL after the task completes.
	integer	No	Video duration in seconds, range , default .
	string	No	Video resolution: or , default .
	boolean	No	Whether to add an AIGC watermark to the generated video. Default .
	string	No	Callback URL after the task completes.
	array<object>	No	Optional for this endpoint (overrides the shared definition above). Required when remixing by source video; the multimodal content array must include a item for the source video.
	string	No	Required when remixing by task ID. Source task ID.
	string	Yes	Video resolution. Fixed to for remix.
	boolean	No	Whether to add an AIGC watermark to the generated video.
	string	No	Callback URL after the task completes.

Request example

H3-Context-IR (text-to-video)

curl --location --request POST 'https://octopusx.ai/v2/h3_context_ir' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "Epic space-opera theatrical trailer: a female captain stands alone before a vast observation window as the last fleet assembles and jumps away; blinding light and a shaking bridge leave her behind."
        }
    ],
    "duration": 5,
    "ratio": "16:9"
}'

H3-Context-IR (first frame + text)

curl --location --request POST 'https://octopusx.ai/v2/h3_context_ir' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "Pull focus to the people in the background and add more steam to the ramen bowl."
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://example.com/image.png"
            },
            "role": "first_frame"
        }
    ],
    "duration": 5,
    "ratio": "adaptive"
}'

H3-Context-IR (reference video + reference audio)

curl --location --request POST 'https://octopusx.ai/v2/h3_context_ir' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "Character speaking: Follow the wind, live free. Leave worries behind, enjoy the moment. Voice tone references audio 1."
        },
        {
            "type": "video_url",
            "video_url": {
                "url": "https://example.com/reference.mp4"
            },
            "role": "reference_video"
        },
        {
            "type": "audio_url",
            "audio_url": {
                "url": "https://example.com/reference.mp3"
            },
            "role": "reference_audio"
        }
    ],
    "duration": 5,
    "ratio": "adaptive"
}'

Text-to-video (t2va)

curl --location --request POST 'https://octopusx.ai/v2/video_generation' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "A cute orange cat playing the piano"
        }
    ],
    "duration": 5,
    "resolution": "2K",
    "aigc_watermark": true
}'

Image-to-video (i2va)

curl --location --request POST 'https://octopusx.ai/v2/video_generation' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "The camera slowly pushes in as the cat starts to play"
        },
        {
            "type": "image_url",
            "image_url": {
                "url": "https://example.com/cat.jpg"
            },
            "role": "first_frame"
        }
    ],
    "duration": 5,
    "resolution": "768P"
}'

By source video (Remix)

curl --location --request POST 'https://octopusx.ai/v2/video_regeneration' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "content": [
        {
            "type": "text",
            "text": "Make the cat play a bit faster"
        },
        {
            "type": "video_url",
            "video_url": {
                "url": "https://example.com/original.mp4"
            }
        }
    ],
    "resolution": "2K"
}'

By task ID (Remix)

curl --location --request POST 'https://octopusx.ai/v2/video_regeneration' \
  --header 'Authorization: Bearer <token>' \
  --header 'Accept: application/json' \
  --header 'Content-Type: application/json' \
  --data-raw '{
    "model": "MiniMax-H3",
    "source_task_id": "426586401755526",
    "resolution": "2K"
}'

Response example

200

{
  "task_id": "426586401755526"
}

200

{
  "task_id": "426586401755527"
}

200

{
  "task_id": "426586401755528"
}

Response fields

Name	Type	Description
	string	Task ID for Task query (official format).

Related endpoints

• MiniMax video overview
• Video APIs overview
• Error codes