# MiniMax H3 | Text to Video

MiniMax H3 Text-to-Video turns written prompts into 5 to 15 second 2K clips with native sound, from cinematic shots to ads and stylized motion design.

## API Information

- **Model Slug:** minimax-h3-text-to-video
- **Branded URL:** https://www.eachlabs.ai/minimax/minimax-h3/minimax-h3-text-to-video
- **Provider:** Minimax
- **Category:** Text to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** MiniMax H3 2K video generation is billed at $0.13 per output second.
- **Estimated Processing Time:** 300 seconds
- **Last Updated:** 2026-08-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/minimax-h3-text-to-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** MiniMax H3 2K video generation is billed at $0.13 per output second.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| resolution == "768P" | MiniMax H3 768P video generation is billed at $0.09 per output second. |
| Rule 2 | MiniMax H3 2K video generation is billed at $0.13 per output second. |

## Input Schema

No input parameters documented.

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax-h3-text-to-video",
  "input": {}
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**MiniMax H3 | Text to Video Overview**

MiniMax H3 | Text to Video is a multimodal generative model from Minimax designed to turn written prompts and visual or audio references into short, cinematic video clips with native stereo sound. It focuses on high-fidelity **2K video** at a film-standard 24 fps, making it well suited for marketing assets, social content, and design explorations that need polished motion in seconds rather than minutes. As part of the Minimax H3 family (also known as Hailuo 3.0), it unifies understanding of text, images, video, and sound to produce 5–15 second clips that already include dialogue, sound effects, and ambience in a single pass. Integrated through each::labs, MiniMax H3 | Text to Video gives creators and developers a fast path from concept to production-ready motion without separate audio pipelines.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.