# MiniMax H3 Max extend video

Needs video url and prompt. Served by fal.ai.

H3 Max Extend Video, served by fal.ai. The OpenAPI schema for the minimax/h3-max/extend-video queue. Price: Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token count. Actual-cost billing: the initial reservation is an estimate, not a maximum. 5 generated seconds at 1080p ($0.16/s), excluding additional reference tokens. The unique Billing Events receipt for this exact endpoint and request_id is the final USD charge, including usage above the estimate. Missing receipts retain the reservation for reconciliation; no guessed final fee. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "minimax/h3-max" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/minimax-h3-max-extend-video`
- Name in the catalog: H3 Max Extend Video
- Provider: [fal.ai](/providers/fal.md)
- Capability: [MiniMax Hailuo](/tools/video-generation/minimax.md)
- Price: usage based, the maximum is shown before a run
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

Billed at the exact provider cost, without a per-call cap. The initial reservation is an estimate; additional usage is debited and unused funds are refunded.


```json
{
  "model": "reported",
  "costPath": "cost_usd",
  "requireCost": true,
  "costMode": "actual",
  "reservationBasis": "5 generated seconds at 1080p ($0.16/s), excluding additional reference tokens.",
  "maxUsdDefault": 0.8,
  "maxUsdCap": 0.8
}
```

Pricing source: [https://fal.ai/models/minimax/h3-max/extend-video](https://fal.ai/models/minimax/h3-max/extend-video). Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token count. Actual-cost billing: the initial reservation is an estimate, not a maximum. 5 generated seconds at 1080p ($0.16/s), excluding additional reference tokens. The unique Billing Events receipt for this exact endpoint and request_id is the final USD charge, including usage above the estimate. Missing receipts retain the reservation for reconciliation; no guessed final fee..

Price verification date: 2026-10-07.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "aspect_ratio": {
      "default": "auto",
      "enum": [
        "auto",
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "title": "Aspect Ratio",
      "description": "Output aspect ratio. 'auto' follows the source video. Other values crop the video to fit the selected ratio.",
      "type": "string"
    },
    "enable_prompt_expansion": {
      "default": true,
      "description": "Automatically enhance the prompt using the source video to help keep the continuation consistent. May increase processing time.",
      "title": "Enable Prompt Expansion",
      "type": "boolean"
    },
    "reference_audio_urls": {
      "description": "Optional audio references for the continuation (2–15 seconds each, 15 seconds combined). The full extended video retains its original source soundtrack, and its ending still conditions the transition. These clips guide the newly generated audio instead of using that soundtrack as an audio reference. Assign each clip a role in the prompt, such as 'Audio 1 for the voice' and 'Audio 2 for background music'.",
      "title": "Reference Audio URLs",
      "items": {
        "type": "string"
      },
      "type": "array",
      "maxItems": 3
    },
    "output": {
      "default": "extended",
      "enum": [
        "extended",
        "continuation"
      ],
      "title": "Output",
      "description": "'extended' returns the source and new footage as one video. 'continuation' returns a clip that starts with a 1.625-second repeat of the source's ending, then shows the new footage.",
      "type": "string"
    },
    "video_url": {
      "description": "URL of the video to extend. Must be 1.625 s to 60 s long, up to 50 MB, aspect ratio between 0.4 and 2.5.",
      "title": "Video Url",
      "minLength": 1,
      "type": "string"
    },
    "duration": {
      "default": 5,
      "maximum": 15,
      "minimum": 0.71,
      "title": "Duration",
      "description": "Seconds of new footage to add. The continuation clip also includes 1.625 seconds from the source's ending and may be longer because of frame rounding.",
      "type": "number"
    },
    "prompt": {
      "description": "What happens next. Describe the continuation, not the source.",
      "title": "Prompt",
      "minLength": 1,
      "maxLength": 50000,
      "type": "string"
    },
    "seed": {
      "description": "Seed for the continuation. Random when omitted.",
      "title": "Seed",
      "anyOf": [
        {
          "type": "integer"
        },
        {
          "type": "null"
        }
      ]
    },
    "enable_safety_checker": {
      "default": true,
      "description": "Moderate the source video and the prompt.",
      "title": "Enable Safety Checker",
      "type": "boolean"
    },
    "resolution": {
      "default": "768P",
      "enum": [
        "480P",
        "768P",
        "1080P",
        "2K"
      ],
      "title": "Resolution",
      "description": "Output video resolution.",
      "type": "string"
    }
  },
  "required": [
    "video_url",
    "prompt"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/minimax-h3-max-extend-video",
  "input": {
    "video_url": "https://storage.googleapis.com/falserverless/example_inputs/flux-3-red-panda.mp4",
    "prompt": "The red panda keeps walking along the log, then looks up at a bird."
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/minimax/h3-max/extend-video)

[REST inspection](https://api.agentik.cc/v1/tools/fal/minimax-h3-max-extend-video) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/minimax-h3-max-extend-video) · [Agent index](/llms.txt)