MiniMax H3 Lite Video Generation

Generate a MiniMax H3 Lite video from 1 to 9 required reference images. Call it via REST API or MCP, or try it in the online playground.

CostEst. 70–84 credits / call

Try online

POST · https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/runMCP · nexscope_minimax_h3_lite_video_generation

Subscription required. Creative AI APIs are available only to users with an active subscription. Trial credits do not enable API key access. View subscription plans.

Video Generation Models

What this API does

Generate a MiniMax H3 Lite video from 1 to 9 required reference images. The request accepts videoTime, prompt, promptOptimizer, isPro, resolution. Generation runs as a task: retain the task ID and retrieve the completed result before using the output.

MiniMax H3 Lite Video Generation API use cases

Draft a product video

To draft a product video, a content editor submits videoTime and prompt to MiniMax H3 Lite Video Generation. The returned completed generation results help review a video concept before campaign production.

Prepare campaign video variants

A content editor uses MiniMax H3 Lite Video Generation with videoTime and prompt to prepare campaign video variants. The returned completed generation results help compare clips created for different campaign briefs.

Review generated footage for a listing

For this workflow, a content editor calls MiniMax H3 Lite Video Generation with videoTime and prompt to review generated footage for a listing. The result helps choose footage suitable for the product listing.

MiniMax H3 Lite Video Generation API FAQ

What does the MiniMax H3 Lite Video Generation API return?

Generate a MiniMax H3 Lite video from 1 to 9 required reference images. It corresponds to the supplied videoTime, prompt, promptOptimizer, isPro, resolution. The initial response can contain a task ID and status; the completed task result contains the generated output. Example values illustrate the response shape, rather than live account results.

How many credits does the MiniMax H3 Lite Video Generation API cost?

The current documented cost is Est. 70–84 credits / call. This is the same cost shown at the top of this page. If a range or estimate is displayed, the final charge depends on the request. Review your available credits and the pricing page before calling the API, and check API usage records for the actual charge.

How do I call the MiniMax H3 Lite Video Generation API from my app or an MCP client?

Send a POST request to https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run with your API key as a Bearer token and the JSON inputs shown in API integration. In a compatible MCP client such as Claude or Cursor, connect Nexscope and call nexscope_minimax_h3_lite_video_generation. The same documented request parameters apply; use Online test to review a request before adding it to your app.

View plans and credits Connect this API with MCP

Try this API

Endpoint

https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run

MCP method

nexscope_minimax_h3_lite_video_generation

Step 1 of 3 · Authenticate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

Missing or invalid API keys return an authentication error. Manage keys from .

Step 2 of 3 · Send a request

POSThttps://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run

Run an API

Generate a MiniMax H3 Lite video from 1 to 9 required reference images.

Example request

Replace YOUR_API_KEY, then run this command in your terminal.

curl -X POST 'https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "imageList": [
    "https://example.com/product.jpg",
    "https://example.com/ref-2.jpg"
  ],
  "prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.",
  "resolution": "768p",
  "videoTime": 5
}'

Step 3 of 3 · Inspect the result

Check the response

Read code for the request status and data for the result. Open the parameter and response reference for the full field definitions.

HTTP status codes

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

View parameters & response Try online

All categories/ Video Generation Models

POSThttps://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run

Run this API

Send a JSON request to execute this API and receive the documented response payload.

Open tester

Endpoint

Method	`POST`
Path	`https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run`
Auth	`Bearer API key`
Content-Type	`application/json`

Request parameters

Name	Type	Required	Description
`videoTime`	`integer`	required	Video duration in seconds. Available options `5` `10` `15` Example: 5
`prompt`	`string`	required	Video generation prompt describing motion, subject consistency, camera movement, and the ecommerce scene. Maximum 10000 characters. Example: Keep the product consistent while the camera slowly orbits and highlights material details.
`promptOptimizer`	`boolean`	optional	Whether Nexscope should optimize the video prompt before generation. Defaults to false. Example: false
`isPro`	`boolean`	optional	Whether to use the model's professional generation mode when supported. Defaults to false. Example: false
`resolution`	`string`	required	Output resolution. Supported values: 768p. Example: 768p
`imageList`	`array`	required	Public reference image URLs. Provide 1 to 9 images. Example: [ "https://example.com/product.jpg", "https://example.com/ref-2.jpg" ]
`aspectRatio`	`string`	optional	- Available options `16:9` `4:3` `1:1` `3:4` `9:16` `21:9` Example: adaptive

Code example

{
  "imageList": [
    "https://example.com/product.jpg",
    "https://example.com/ref-2.jpg"
  ],
  "prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.",
  "resolution": "768p",
  "videoTime": 5
}

Response example

Platform response envelope. code 0 indicates success or acceptance; data contains the business result.

{
  "code": 0,
  "cost": "-1",
  "data": {
    "result": null,
    "status": "PENDING",
    "taskId": "example-task"
  },
  "msg": null,
  "time": "2026-01-01 00:00:00",
  "traceId": null,
  "ts": "0"
}

Response fields

Name	Type	Required	Description
`code`	`integer`	required	0 means accepted or successful; nonzero is a platform error.
`cost`	`string`	required	Elapsed milliseconds, never credits; -1 outside web requests.
`data`	`any`	required	Data value used by this API operation.
`msg`	`string \| null`	required	Msg value used by this API operation.
`time`	`string`	required	Server local time: yyyy-MM-dd HH:mm:ss.
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds.

Any of option 1 — requires taskId, status, result

Name	Type	Required	Description
`data`	`object`	required	Data value used by this API operation.
`data.result`	`any`	required	Result value used by this API operation.
`data.status`	`string`	required	Status value used by this API operation. Allowed: PENDING, RUNNING, SUCCEEDED, FAILED, TIMEOUT
`data.taskId`	`string`	required	Task id value used by this API operation.

Any of option 1

Name	Type	Required	Description
`data.result`	`object`	required	Completed generation output retained from the task result. Fields vary by capability; generated resources use Nexscope-hosted URLs and any count represents charged Nexscope credits. This is the business output, not a task creation receipt.

Any of option 2

Name	Type	Required	Description
`data.result`	`null`	required	Result value used by this API operation.

Any of option 2

Name	Type	Required	Description
`data`	`null`	required	Data value used by this API operation.

Responses

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

Data source, freshness, and limitations

Source, freshness, coverage, rate limits, and estimation notes are not specified in this API definition unless they appear in the request or response field documentation above. Do not assume official marketplace data or real-time freshness when it is not explicitly documented.

Step 1 of 2 · Connect your MCP client

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/api/skill-api/v2/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json

Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Step 2 of 2 · Call the tool

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_minimax_h3_lite_video_generation",
    "arguments": {
      "imageList": [
        "https://example.com/product.jpg",
        "https://example.com/ref-2.jpg"
      ],
      "prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.",
      "resolution": "768p",
      "videoTime": 5
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /api/skill-api/v1/mcp

Online test

Execute the current API with your API key and JSON payload. Online tests use this site's configured API environment; the Endpoint and copyable examples use the public integration address.

Create a video

Prompt*0/10,000

Reference images*Required

JPG, PNG, WEBP · Up to 9 images · 20 MB each

0/9

Video settings

Duration*

Improve prompt

Model default

Pro mode

Model default · May use more credits.

Resolution*

768P (fixed)

Aspect ratio

API keys require an active subscription. Trial credits don't include API access. View plans.

Usage estimate unavailable

Final credits are shown with your result.

Preview

Your video will appear here

Recent generations

Saved in this browser for 24 hours

Your generations will appear here.

Test with an API key or MCP

Try it

Send a real request with the same contract shown in the reference.

Endpoint

https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run

Task result endpoint

https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/tasks/{taskId}

MCP method

nexscope_minimax_h3_lite_video_generation

API key*

JSON payload*

cURL

curl -X POST \
  https://api.nexscope.ai/api/skill-api/v1/skills/minimax-h3-lite-video-generation/run \
  -H "Authorization: Bearer nk-..." \
  -H "Content-Type: application/json" \
  -d '{ "imageList": [], "prompt": "Keep the product consistent while the camera slowly orbits and highlights material details.", "resolution": "768p", "videoTime": 5 }'

Response

No response yet. Run the request to see the response here.

Task result

Results are checked automatically after Run request. You can also enter a task ID and check it manually; completed resources use Nexscope URLs and show actual charged credits.

Task ID

Result response

No task result yet. Query the task to see the generated output here.

Related APIs

Hailuo 2.3 Video Generation

Generate a Hailuo 2.3 video from a required primary image; the aspect ratio is adaptive.

Happy Horse 2 Video Generation

Generate a Happy Horse 2 video from 1 to 9 required reference images.

Kling 2.6 Video Generation

Generate a Kling 2.6 video using a first frame, first/last frames, or up to 2 reference images.

Kling 3 Omni Video Generation

Generate a Kling 3 Omni video using first/last frames or up to 7 reference images.