> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> The Venice API is OpenAI-compatible: use any OpenAI SDK with the base URL `https://api.venice.ai/api/v1` and a Venice API key, or pay per request from a USDC wallet through x402 with no account.
> Read model IDs from `GET /models` or `GET /models/traits` at runtime instead of hardcoding them from memory or from these pages. Models are added and retired often.
> Every model's price is in https://docs.venice.ai/pricing.md. Quote video and audio jobs with `POST /video/quote` or `POST /audio/quote` before you queue them.
> Search these docs from an MCP client at https://docs.venice.ai/mcp. The full agent guide is https://docs.venice.ai/agents.md.

# MiniMax H3 Max Recast API

> MiniMax H3 Max Recast API on Venice: video editing, up to 1080p, priced per clip with /video/quote. Private, with zero data retention.



## MiniMax H3 Max Recast API

MiniMax H3 Max Recast is a video editing model by MiniMax, available on the Venice API as `minimax-h3-max-recast`. This model is private and no prompt data is stored in any capacity.

MiniMax H3 Max Recast replaces the people in a source video with people from reference photos, preserving the original motion, camera, cuts and soundtrack, at up to 1080p.

### MiniMax H3 Max Recast API pricing

| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `minimax-h3-max-recast` | Video edit | Private | priced by source |

### MiniMax H3 Max Recast specifications

| Spec | Value |
| - | - |
| Provider | MiniMax |
| Released | Oct 7, 2026 |
| Privacy | Private |
| Status | Stable |
| Modes | video editing |
| Resolutions | 768p, 1080p |
| Durations | Auto |
| Audio | None |

### How to use the MiniMax H3 Max Recast API

Send requests to `POST https://api.venice.ai/api/v1/video/queue` with `"model": "minimax-h3-max-recast"` and your API key.

```bash theme={"system"}
# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/video/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3-max-recast",
    "prompt": "Recast the person in the video as the person in the reference image",
    "resolution": "768P",
    "reference_image_urls": ["https://example.com/character.jpg"],
    "video_url": "https://example.com/source.mp4"
  }'

# 2. Poll until the MP4 is ready (JSON with the status until then)
curl https://api.venice.ai/api/v1/video/retrieve \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "minimax-h3-max-recast", "queue_id": "<queue_id>" }' --output video.mp4

# If the queue response has a download_url, retrieve only reports the
# status: download the MP4 from that URL once it is COMPLETED.
```

### Related models

* [Grok Imagine 1.5 Lite API](https://docs.venice.ai/models/grok-imagine-1-5-lite.md): from \$0.024 / sec
* [Flux 3 Max API](https://docs.venice.ai/models/flux-3-max.md): from \$0.1276 / sec
* [Kling 4.0 API](https://docs.venice.ai/models/kling-4-0.md): from \$0.1963 / sec
* [Kling 4.0 Flash API](https://docs.venice.ai/models/kling-4-0-flash.md): from \$0.1174 / sec


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.