MiniMax: H3 (Text to Video) API Reference

About

MiniMax H3 is a frontier video model. This endpoint generates video from a text prompt alone, rendering at 2K in durations from 5 to 15 seconds across seven aspect ratios.

1. Calling the API

Setup your API Key

To begin using Infron, you first need to create an account and generate your API Key.

Once you have your API key, set it as an environment variable in your runtime environment. This allows your applications to securely access Infron’s API.

export INFRON_KEY="YOUR_API_KEY"

Submit a request

For long-running requests, you can poll for results.

curl https://media.onerouter.pro/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/minimax-h3/text-to-video",
  "prompt": "Two adult fantasy warriors in a stylized choreographed duel on a rain-slicked rooftop at night. One channels crackling blue-white energy, the other radiant orange light. They close the distance at high speed, exchanging blocks, parries, and glancing sweeps of glowing energy blades, then meet in a mid-air clash that bursts into colored sparks, light trails, and scattering rain. Sweeping camera, dramatic close-ups on hands and faces, exaggerated stylized motion, vibrant rim lighting, high contrast, ending on a heroic standoff pose. Non-violent stylized action, no blood, no injury, no gore, no weapons contact with bodies. Original character designs.",
  "aspect_ratio": "16:9",
  "duration": 5,
  "resolution": "2K",
  "watermark": false
}'

Response with queue task id

The response will look like this:

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "20260831024755433036026eyv0ptDz",
    "object": "video",
    "model": "minimax/minimax-h3/text-to-video",
    "status": "created",
    "urls": {
      "query": "https://media.onerouter.pro/v1/videos/tasks/20260831024755433036026eyv0ptDz"
    },
    "created_at": "2026-08-31 02:47:55.45"
  }
}

Fetch request status

You can fetch the status of a request to check if it is completed or still in progress.

curl https://media.onerouter.pro/v1/videos/tasks/{task_id} \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" 

# For example
curl https://media.onerouter.pro/v1/videos/tasks/20260831024755433036026eyv0ptDz \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json"

Response with queue task status query

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "20260831024755433036026eyv0ptDz",
    "object": "video",
    "model": "minimax/minimax-h3/text-to-video",
    "status": "in_progress",
    "fail_reason": "",
    "submit_time": 1788144475,
    "start_time": 1788144475,
    "finish_time": 0,
    "outputs": [],
    "created_at": "2026-08-31 02:47:55"
  }
}

Possible statuses:

  • created
  • in_progress
  • processing
  • completed
  • failed

created -> in_progress → processing → completed | failed

Poll every 1-2 seconds until status is "completed" or "failed"

Get the result (when status is "completed")

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "20260831024755433036026eyv0ptDz",
    "object": "video",
    "model": "minimax/minimax-h3/text-to-video",
    "status": "completed",
    "fail_reason": "",
    "submit_time": 1788144475,
    "start_time": 1788144475,
    "finish_time": 1788144702,
    "outputs": [
      "https://infron.ai/cdn/media/video/video_v2/output/output_68c4f778-9333-4d83-b3c2-46f0b3e5cd2d.mp4"
    ],
    "usage": {
      "completion_tokens": 0,
      "duration": 5,
      "generate_audio": true,
      "output_count": 1,
      "prompt_tokens": 1,
      "request_num": 1,
      "resolution": "2K",
      "tokens": 1,
      "total_tokens": 1,
      "video_duration": 5
    },
    "cost": {
      "total_cost": 0.65,
      "cost_details": {
        "prompt_cost": 0,
        "completion_cost": 0,
        "image_cost": 0,
        "video_cost": 0.65,
        "audio_cost": 0,
        "native_web_search_cost": 0,
        "plugin_web_search_cost": 0,
        "tools_cost": 0,
        "prompt_cache_read_cost": 0,
        "prompt_cache_write_cost": 0,
        "prompt_cache_write_5_min": 0,
        "prompt_cache_write_1_h": 0,
        "reasoning_cost": 0,
        "discount_rate": 1,
        "is_byok": false,
        "byok_cost": 0
      }
    },
    "created_at": "2026-08-31 02:47:55"
  }
}

2. Schema

Input

ParameterTypeRequiredDefaultRangeDescription
modelstringYes--Explore all modelsModel name.
promptstringYes----Text prompt for generation; Positive text prompt.
aspect_ratiostringNo16:921:9, 16:9, 4:3, 1:1, 3:4, 9:16Aspect ratio of the generated video
durationintegerNo44, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15Duration of the generated video
resolutionstringNo2K768P, 2KResolution of the generated video
watermarkbooleanNoFalsetrue, falseWhether to generate watermark.

Example request

curl https://media.onerouter.pro/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/minimax-h3/text-to-video",
  "prompt": "Two adult fantasy warriors in a stylized choreographed duel on a rain-slicked rooftop at night. One channels crackling blue-white energy, the other radiant orange light. They close the distance at high speed, exchanging blocks, parries, and glancing sweeps of glowing energy blades, then meet in a mid-air clash that bursts into colored sparks, light trails, and scattering rain. Sweeping camera, dramatic close-ups on hands and faces, exaggerated stylized motion, vibrant rim lighting, high contrast, ending on a heroic standoff pose. Non-violent stylized action, no blood, no injury, no gore, no weapons contact with bodies. Original character designs.",
  "aspect_ratio": "16:9",
  "duration": 5,
  "resolution": "2K",
  "watermark": false
}'

Output

ParameterTypeRangeDescription
codeinteger--Status code of the request.
messagestring--Status message of the request.
dataobject--Data of the video task.
data.task_idstring--ID of the video task.
data.objectstring--Object type of the video task.
data.modelstring--Model name of the video task.
data.statusstringcreated, in_progress, processing, completed, failedStatus of the video task.
data.fail_reasonstring--Fail reason of the video task.
data.submit_timeinteger--Timestamp of the video task submission.
data.start_timeinteger--Timestamp of the video task start.
data.finish_timeinteger--Timestamp of the video task finish.
data.outputsarray--Outputs of the video task.
data.created_atstring--Timestamp of the video task creation.

Example output

{
  "code": 200,
  "message": "success",
  "data": {
    "task_id": "20260831024755433036026eyv0ptDz",
    "object": "video",
    "model": "minimax/minimax-h3/text-to-video",
    "status": "completed",
    "fail_reason": "",
    "submit_time": 1788144475,
    "start_time": 1788144475,
    "finish_time": 1788144702,
    "outputs": [
      "https://infron.ai/cdn/media/video/video_v2/output/output_68c4f778-9333-4d83-b3c2-46f0b3e5cd2d.mp4"
    ],
    "usage": {
      "completion_tokens": 0,
      "duration": 5,
      "generate_audio": true,
      "output_count": 1,
      "prompt_tokens": 1,
      "request_num": 1,
      "resolution": "2K",
      "tokens": 1,
      "total_tokens": 1,
      "video_duration": 5
    },
    "cost": {
      "total_cost": 0.65,
      "cost_details": {
        "prompt_cost": 0,
        "completion_cost": 0,
        "image_cost": 0,
        "video_cost": 0.65,
        "audio_cost": 0,
        "native_web_search_cost": 0,
        "plugin_web_search_cost": 0,
        "tools_cost": 0,
        "prompt_cache_read_cost": 0,
        "prompt_cache_write_cost": 0,
        "prompt_cache_write_5_min": 0,
        "prompt_cache_write_1_h": 0,
        "reasoning_cost": 0,
        "discount_rate": 1,
        "is_byok": false,
        "byok_cost": 0
      }
    },
    "created_at": "2026-08-31 02:47:55"
  }
}

3. Detailed Pricing

ResolutionBilled unitPrice
768p1 output video second$0.08
2k1 output video second$0.13
768p → 2k regeneration1 output video second$0.05
reference video → 768p1 input video second$0.08
reference video → 2k1 input video second$0.13
additional image (>5)1 input image$0.04
audio1 input audioFree