MiniMax H3 X API reference
2–15-second videos with sound, up to 1080p
Call MiniMax H3 X from your own code with one PopNow API key. Below are the exact model IDs to send, every input field the model accepts, what each request costs in USD, and a request you can paste into a terminal.
At a glance
- Made by
- MiniMax
- Output
- Video
- From
- $0.022 USD per second of output
- Typical time
- about 156 s
Prices are in USD, charged to your separate API wallet. A task reserves the maximum possible charge when accepted and settles actual usage on completion; any remainder is released. Failed tasks are not charged. Call POST /api/v1/jobs/quote for an exact quote before running.
Create Video
minimax/h3-x/text-to-video
Price
| Option | USD |
|---|---|
480p | $0.022 per second of output |
720p | $0.032 per second of output |
1080p | $0.045 per second of output |
Parameters
| Field | Type | Default | Allowed | What it does |
|---|---|---|---|---|
promptRequired | string | — | up to 7,000 characters | Describe the scene, the action, spoken lines in double quotes, the camera and the sound. Timed shots ("At 5 seconds the shot cuts to…") are followed. |
aspect_ratioOptional | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 | Output aspect ratio. |
resolutionOptional | string | 720p | 480p, 720p, 1080p | Output resolution. 1080p gives a bigger frame, not visibly more detail than 720p. |
duration_secondsOptional | integer | 5 | 2 to 15 | Output length in whole seconds, from 2 to 15. Billed per second. |
enable_prompt_expansionOptional | boolean | false | — | Let the built-in prompt enhancer rewrite and expand your prompt before generating. Keep it off for literal direction. |
Example request
This request runs as it is; any field you leave out uses its default. Put your key in POPNOW_API_KEY first.
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "minimax/h3-x/text-to-video",
"input": {
"prompt": "A paper boat drifts down a rain-soaked street at dusk, neon signs reflecting in the water, slow tracking shot at ground level",
"duration_seconds": 5,
"resolution": "720p"
}
}'The response carries a taskId straight away. Read the result with GET /api/v1/jobs/recordInfo, or add callBackUrl to be notified.
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"Image to Video
minimax/h3-x/image-to-video
Price
| Option | USD |
|---|---|
480p | $0.022 per second of output |
720p | $0.032 per second of output |
1080p | $0.045 per second of output |
Parameters
| Field | Type | Default | Allowed | What it does |
|---|---|---|---|---|
promptRequired | string | — | up to 7,000 characters | Describe what happens after the opening frame: the action, spoken lines in double quotes, the camera and the sound. |
image_urlRequired | string (uri) | — | — | Opening frame. The clip starts from this image and keeps its shape. |
last_image_urlOptional | string (uri) | — | — | Optional closing frame. The clip ends on this image. |
resolutionOptional | string | 720p | 480p, 720p, 1080p | Output resolution. 1080p gives a bigger frame, not visibly more detail than 720p. |
duration_secondsOptional | integer | 5 | 2 to 15 | Output length in whole seconds, from 2 to 15. Billed per second. |
enable_prompt_expansionOptional | boolean | false | — | Let the built-in prompt enhancer rewrite and expand your prompt before generating. Keep it off for literal direction. |
Example request
This request runs as it is; any field you leave out uses its default. Put your key in POPNOW_API_KEY first.
The example uses PopNow sample files in image_url. Replace them with your own public HTTPS links, uploads or saved assets.
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "minimax/h3-x/image-to-video",
"input": {
"prompt": "He lands softly on the rooftop, laughs and turns toward the camera while the balloons sway in the evening breeze; slow push-in",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"duration_seconds": 5,
"resolution": "720p"
}
}'The response carries a taskId straight away. Read the result with GET /api/v1/jobs/recordInfo, or add callBackUrl to be notified.
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"Reference to Video
minimax/h3-x/reference-to-video
Price
| Option | USD |
|---|---|
480p | $0.022 per second of output |
720p | $0.032 per second of output |
1080p | $0.045 per second of output |
Parameters
| Field | Type | Default | Allowed | What it does |
|---|---|---|---|---|
promptRequired | string | — | up to 7,000 characters | Describe the scene and refer to each reference by type and position: "the woman from Image 1", "the motion of Video 1", "the voice of Audio 1". |
reference_image_urlsOptional | array<string (uri)> | — | up to 9 items | Up to nine reference images: people, outfits, products or places, in the order your prompt refers to them. The first five are included; each image after the fifth adds a small charge. |
reference_video_urlsOptional | array<string (uri)> | — | up to 2 items | Up to two reference videos, 15 seconds in total, for a motion or a scene to follow. Their seconds are billed like output seconds. |
reference_audio_urlsOptional | array<string (uri)> | — | up to 3 items | Up to three reference audio clips for a voice or a sound. The spoken words still go in the prompt. |
aspect_ratioOptional | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 | Output aspect ratio. |
resolutionOptional | string | 720p | 480p, 720p, 1080p | Output resolution. 1080p gives a bigger frame, not visibly more detail than 720p. |
duration_secondsOptional | integer | 5 | 2 to 15 | Output length in whole seconds, from 2 to 15. Billed per second. |
enable_prompt_expansionOptional | boolean | false | — | Let the built-in prompt enhancer rewrite and expand your prompt before generating. Keep it off for literal direction. |
Example request
This request runs as it is; any field you leave out uses its default. Put your key in POPNOW_API_KEY first.
The example uses PopNow sample files in reference_image_urls. Replace them with your own public HTTPS links, uploads or saved assets.
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "minimax/h3-x/reference-to-video",
"input": {
"prompt": "The man from the reference image jogs across a sunlit rooftop at golden hour and smiles at the camera; smooth tracking shot",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"duration_seconds": 5,
"resolution": "720p"
}
}'The response carries a taskId straight away. Read the result with GET /api/v1/jobs/recordInfo, or add callBackUrl to be notified.
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"