minimax/h3-max/text-to-video

testo-in-video

MiniMax H3 Max Text-to-Video API by MiniMax

minimax/h3-max/text-to-video

Text-to-video

MiniMax H3 Max text-to-video: generate a cinematic video from a text prompt. Supports 480P、768P, 5-15s., and 16:9/9:16/1:1/adaptive aspect ratios.

Confronta modelli

MiniMax H3 Max Text-to-Video è sviluppato da MiniMax. Atlas Cloud (gestita da Atlas Cloud AI LLC) ne fornisce l’accesso ma non ne è proprietaria. Tutti i marchi appartengono ai rispettivi titolari.

INPUT

Prompt *

Risoluzione *

Durata *

Proporzioni

Prompt expansion

OUTPUT

In attesa

I video generati appariranno qui

Configura le impostazioni e clicca Esegui per iniziare

La tua richiesta costerà $0.048 per esecuzione. Con $10 puoi eseguire questo modello circa 208 volte.

Ecco cosa puoi fare dopo:

Seedance 2.0 Kling v3 Vidu Wan2.7

Parametri

Esempio di codice
import requests
import time

# Step 1: Start video generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "minimax/h3-max/text-to-video",  # Required. model name
    "prompt": "A beautiful sunset over the ocean with gentle waves",  # Required. The text prompt describing the video to generate
    "resolution": "768P",  # Required. Native 480P or 768P output, or SR-enhanced 1440P or 4K short edge. options: 480P | 768P | 1440p-sr | 4k-sr
    "duration": 8,  # Required. The duration of the generated video in seconds
    "ratio": "1:1",  # The aspect ratio of the generated video. options: 21:9 | 16:9 | 4:3 | 1:1 | 3:4 | 9:16
    "prompt_expansion": False,  # Whether to expand the prompt for better results
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] in ["completed", "succeeded"]:
            print("Generated video:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

video_url = check_status()

Installa

Installa il pacchetto di dipendenze richiesto.

pip install requests

Autenticazione

Tutte le richieste API richiedono l'autenticazione tramite una chiave API. Puoi ottenere la tua chiave API dalla dashboard di Atlas Cloud.

export ATLASCLOUD_API_KEY="your-api-key-here"

Header HTTP

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

Proteggi la tua chiave API

Non esporre mai la tua chiave API nel codice lato client o nei repository pubblici. Utilizza invece variabili d'ambiente o un proxy backend.

Invia una richiesta

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "prompt": "A beautiful landscape"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Invia una richiesta

Invia una richiesta di generazione asincrona. L'API restituisce un ID di previsione che puoi usare per controllare lo stato e recuperare il risultato.

POST/api/v1/model/generateVideo

Corpo della richiesta

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "minimax/h3-max/text-to-video",
    "prompt": "A beautiful sunset over the ocean with gentle waves"
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

Risposta

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

Controlla lo stato

Interroga l'endpoint di previsione per verificare lo stato attuale della tua richiesta.

GET/api/v1/model/prediction/{prediction_id}

Esempio di polling

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

Valori di stato

processingLa richiesta è ancora in fase di elaborazione.

completedGenerazione completata. Gli output sono disponibili.

succeededGenerazione riuscita. Gli output sono disponibili.

failedLa generazione è fallita. Controlla il campo errore.

Risposta completata

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.mp4"
    ],
    "metrics": {
      "predict_time": 45.2
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

Carica file

Carica file nello storage Atlas Cloud e ottieni un URL utilizzabile nelle tue richieste API. Usa multipart/form-data per il caricamento.

POST/api/v1/model/uploadMedia

Esempio di caricamento

import requests

url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

with open("image.png", "rb") as f:
    files = {"file": ("image.png", f, "image/png")}
    response = requests.post(url, headers=headers, files=files)

result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")

Risposta

{
  "data": {
    "download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
    "file_name": "image.png",
    "content_type": "image/png",
    "size": 1024000
  }
}

Schema di input

I seguenti parametri sono accettati nel corpo della richiesta.

Totale: 6Obbligatorio: 4Opzionale: 2

modelstringrequired

model name

Default: "minimax/h3-max/text-to-video"

promptstringrequired

The text prompt describing the video to generate.

resolutionstringrequired

Native 480P or 768P output, or SR-enhanced 1440P or 4K short edge.

Default: "768P"

480P768P1440p-sr4k-sr

durationnumberrequired

The duration of the generated video in seconds.

Default: 8

56789101112131415

ratiostring

The aspect ratio of the generated video.

Default: "1:1"

21:916:94:31:13:49:16

prompt_expansionboolean

Whether to expand the prompt for better results.

Default: false

Esempio di corpo della richiesta

{
  "model": "minimax/h3-max/text-to-video",
  "prompt": "A beautiful landscape",
  "resolution": "768P",
  "duration": 8,
  "ratio": "1:1",
  "prompt_expansion": false
}

Schema di output

L'API restituisce una risposta di previsione con gli URL degli output generati.

created_atstring

ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).

idstring

Unique identifier for the prediction, the ID of the prediction to get.

modelstring

Model ID used for the prediction.

outputsarray

Array of URLs to the generated content (empty when status is not completed).

statusstring

Status of the task: created, processing, completed, or failed.

Esempio di risposta

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.mp4"
  ],
  "metrics": {
    "predict_time": 45.2
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills integra oltre 400 modelli di IA direttamente nel tuo assistente di codifica IA. Un comando per installare, poi usa il linguaggio naturale per generare immagini, video e chattare con LLM.

Client supportati

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ client supportati

Installa

npx skills add AtlasCloudAI/atlas-cloud-skills

Configura chiave API

Ottieni la tua chiave API dalla dashboard di Atlas Cloud e impostala come variabile d'ambiente.

export ATLASCLOUD_API_KEY="your-api-key-here"

Funzionalità

Una volta installato, puoi usare il linguaggio naturale nel tuo assistente IA per accedere a tutti i modelli Atlas Cloud.

Generazione di immaginiGenera immagini con modelli come Nano Banana 2, Z-Image e altri.

Creazione di videoCrea video da testo o immagini con Kling, Vidu, Veo, ecc.

Chat LLMChatta con Qwen, DeepSeek e altri grandi modelli linguistici.

Caricamento mediaCarica file locali per la modifica di immagini e flussi di lavoro da immagine a video.

Scopri di più

github.com/AtlasCloudAI/atlas-cloud-skills

Server MCP

Il server MCP di Atlas Cloud collega il tuo IDE con oltre 400 modelli di IA tramite il Model Context Protocol. Funziona con qualsiasi client compatibile MCP.

Client supportati

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ client supportati

Installa

npx -y atlascloud-mcp

Configurazione

Aggiungi la seguente configurazione al file delle impostazioni MCP del tuo IDE.

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

Strumenti disponibili

atlas_generate_imageGenera immagini da prompt testuali.

atlas_generate_videoCrea video da testo o immagini.

atlas_chatChatta con grandi modelli linguistici.

atlas_list_modelsEsplora oltre 400 modelli di IA disponibili.

atlas_quick_generateCreazione di contenuti in un solo passaggio con selezione automatica del modello.

atlas_upload_mediaCarica file locali per i flussi di lavoro API.

Scopri di più

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "minimax/h3-max/text-to-video"
          },
          "prompt": {
            "description": "The text prompt describing the video to generate.",
            "type": "string"
          },
          "resolution": {
            "default": "768P",
            "description": "Native 480P or 768P output, or SR-enhanced 1440P or 4K short edge.",
            "enum": [
              "480P",
              "768P",
              "1440p-sr",
              "4k-sr"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "duration": {
            "default": 8,
            "description": "The duration of the generated video in seconds.",
            "enum": [
              5,
              6,
              7,
              8,
              9,
              10,
              11,
              12,
              13,
              14,
              15
            ],
            "type": "number",
            "x-ui-component": "select"
          },
          "ratio": {
            "default": "1:1",
            "description": "The aspect ratio of the generated video.",
            "enum": [
              "21:9",
              "16:9",
              "4:3",
              "1:1",
              "3:4",
              "9:16"
            ],
            "type": "string",
            "x-ui-component": "select"
          },
          "prompt_expansion": {
            "default": false,
            "description": "Whether to expand the prompt for better results.",
            "type": "boolean",
            "x-ui-component": "switch"
          }
        },
        "required": [
          "model",
          "prompt",
          "resolution",
          "duration"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "prompt",
          "resolution",
          "duration",
          "ratio",
          "prompt_expansion"
        ]
      },
      "PredictionResponse": {
        "properties": {
          "created_at": {
            "description": "ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).",
            "format": "date-time",
            "type": "string"
          },
          "id": {
            "description": "Unique identifier for the prediction, the ID of the prediction to get.",
            "type": "string"
          },
          "model": {
            "description": "Model ID used for the prediction.",
            "type": "string"
          },
          "outputs": {
            "description": "Array of URLs to the generated content (empty when status is not completed).",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "description": "Status of the task: created, processing, completed, or failed.",
            "type": "string"
          },
          "urls": {
            "description": "Object containing related API endpoints.",
            "type": "object"
          }
        },
        "type": "object"
      }
    },
    "securitySchemes": {
      "apiKeyAuth": {
        "in": "header",
        "name": "Authorization",
        "type": "apiKey"
      }
    }
  },
  "info": {
    "description": "The AtlasCloud API.",
    "title": "AtlasCloud API",
    "version": "1.0.0"
  },
  "openapi": "3.0.0",
  "paths": {
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "required": true,
            "schema": {
              "description": "Request ID",
              "type": "string"
            }
          }
        ],
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        },
        "x-api-name": "model_result"
      }
    },
    "/api/v1/model/generateVideo": {
      "post": {
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          },
          "required": true
        },
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        },
        "x-api-name": "model_run"
      }
    }
  },
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ]
}

Template di prompt ottimizzato per LLM

# minimax/h3-max/text-to-video

> MiniMax H3 Max text-to-video: generate a cinematic video from a text prompt. Supports 480P、768P, 5-15s., and 16:9/9:16/1:1/adaptive aspect ratios.


## Overview

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `minimax/h3-max/text-to-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"minimax/h3-max/text-to-video"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the video to generate.

- **`resolution`** (`string`, _required_):
  Native 480P or 768P output, or SR-enhanced 1440P or 4K short edge.
  - Default: `"768P"`
  - Options: "480P", "768P", "1440p-sr", "4k-sr"

- **`duration`** (`number`, _required_):
  The duration of the generated video in seconds.
  - Default: `8`
  - Options: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

- **`ratio`** (`string`, _optional_):
  The aspect ratio of the generated video.
  - Default: `"1:1"`
  - Options: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"

- **`prompt_expansion`** (`boolean`, _optional_):
  Whether to expand the prompt for better results.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "minimax/h3-max/text-to-video",
  "prompt": "",
  "resolution": "768P",
  "duration": 8
}
```


**Full Example**:

```json
{
  "model": "minimax/h3-max/text-to-video",
  "prompt": "",
  "resolution": "768P",
  "duration": 8,
  "ratio": "1:1",
  "prompt_expansion": false
}
```


### Output Schema

The API returns the following output format:


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction, the ID of the prediction to get.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated content (empty when status is not completed).

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "created_at": "",
  "id": "",
  "model": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3-max/text-to-video",
  "prompt": "",
  "resolution": "768P",
  "duration": 8,
  "ratio": "1:1",
  "prompt_expansion": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/minimax/h3-max/text-to-video)

A tiny hamster wearing a miniature explorer's outfit walks through a vast golden wheat field at sunset, carrying a small red gift box. A gentle breeze moves the wheat, warm sunlight shines through the clouds, and the hamster suddenly stops as a flock of birds flies across the glowing sky. The camera slowly tracks behind the hamster, then moves into a cinematic close-up as it looks toward a distant cozy cottage. Emotional storytelling, cinematic composition, warm golden-hour lighting, shallow depth of field, subtle film grain, realistic fur details, natural movement, atmospheric, magical yet believable, 4K, cinematic film style.

Caricamento...

MiniMax H3 Max Text-to-Video

MiniMax H3 Max Text-to-Video is a speed-optimized AI video generation model that turns a text prompt into a complete 24fps clip with synchronized audio. A 5-second 768P video renders in under 3 seconds, and even a full 15-second clip finishes in roughly 15 seconds — fast enough to iterate on an idea in real time rather than waiting on a queue.

Why Choose This?

Near-instant generation A 5s 768P clip in under 3 seconds; 15s clips in about 15 seconds.
Audio included Every clip is generated as complete audio-video at 24fps — no separate scoring or sound pass.
Cinematic motion Fluid camera work and lifelike movement from a plain-text description.
Flexible aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16 to fit any platform.
Selectable duration Produce 5–15s clips at 480P or 768P.

Parameters

Parameter	Required	Description
prompt	Yes	Text description of the scene, subject, and action
resolution	Yes	Video resolution. Available options: `480P`, `768P`
duration	Yes	Duration of the generated video in seconds. Integer between 4 and 15. Available options: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
ratio	Yes	Aspect ratio of the generated video. For text-to-video, `ratio` is required and cannot be `adaptive`. Available options: `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`
prompt_expansion	No	Enable AI prompt expansion via H3 Context-IR. When `true`, your prompt is first expanded into a rich, structured description (shot, soundscape, music) before generation, and an additional per-token Context-IR fee applies. Default `false`: the prompt is used as-is with no extra charge.
callback_url	No	HTTPS URL notified whenever the task status changes, so you can react to completion without polling. Requires a one-time verification handshake — see Task Status Callbacks below.

Task Status Callbacks (`callback_url`)

When you supply a callback_url, the MiniMax server notifies it on every task status change, so you don't have to poll for the result.

Verification handshake — right after the task is created, the server first sends a verification request to your URL containing a challenge field. Your endpoint must return the challenge value unchanged, within 3 seconds, to complete verification.
Status pushes — once verification succeeds, the server sends a POST to your URL every time the task status changes. The push body has the same structure as the Query Task (task status) response.

Callback status values: queued, running, succeeded, failed, cancelled.

The callback_url must be a publicly reachable HTTPS endpoint.

How to Use

Write your prompt — describe the scene, subject, lighting, and motion in detail.
Set resolution — higher for quality, lower for faster generation.
Choose an aspect ratio — pick one of the supported ratios; adaptive is not available for text-to-video.
Adjust duration — pick any length from 5s to 15s.
Run — submit and download your video.

Best Use Cases

Social Media Content — Short-form clips for TikTok, Reels, and Stories.
Concept Visualization — Bring ideas to life without filming.
Marketing Videos — Produce promotional content from text.
Storytelling — Create narrative scenes for creative projects.

Pro Tips

Be specific about camera angle, lighting, mood, and motion.
For text-to-video, ratio must be an explicit value (e.g. 16:9); adaptive is not supported for this mode.
Describe environmental effects (wind, smoke, golden-hour light) for richer results.

Notes

A prompt is required.
Supported durations between 5s and 15s, at 24fps with audio.
Resolution is limited to 480P and 768P — 2K is not available on H3 Max.
Keyframe interpolation and multimodal references (reference image / video / audio) are not supported.
Generation is asynchronous — submit, then poll for the finished video.

MiniMax H3 Max Image-to-Video — Animate a first-frame image at the same speed.
MiniMax H3 Text-to-Video — The standard H3 model, with 2K output and reference-to-video support.