MiniMaxMiniMax H3 Max API

Name: MiniMax H3 Max API
Price: 0.03 USD
Author: MiniMax

Top-tier MiniMax H3 Max video from text, a start/end frame, or reference images, videos, and audio — refer to references in the prompt as Image 1, Video 1, Audio 1, in input order. Up to 15s at 1080p.

Prompt

Reference inputs

Duration

Resolution

Aspect ratio

Billed at this model’s published rate.

Result

Your generations will appear here

Other models from MiniMax

Same vendor, same API call — the differences are below.

Model	Use case	Price	Resolution	Duration	Added
MiniMax H3 Max Recast	Video → Video	from $0.33 / sec	768p · 1080p	—	Nov 2026
MiniMax H3 Highspeed	Text → Video	from $0.0352 / sec	480P · 768P	5–15s	Nov 2026
MiniMax H3 Lite	Text → Video	from $0.022 / sec	480P · 768P	5–15s	Nov 2026
MiniMax M3	Image → Text	from $0.06 / 1M cached in	—	—	Oct 2026
MiniMax M3.1 Flash	Image → Text	from $0.015 / 1M cached in	—	—	Oct 2026
MiniMax H3 Context IR	Video → Text	from $0.45 / 1M in	—	4–15s	Oct 2026
MiniMax H3 Max Relight	Video → Video	from $0.055 / sec	480p · 768p · 1080p …	—	Oct 2026
MiniMax H3 Max Extend	Video → Video	from $0.055 / sec	480p · 768p · 1080p …	5–15s	Sep 2026

Install the SDK

TypeScript targets Node 20+ and ships with types; Python needs 3.10+ and is async. Over REST there is nothing to install: call https://api.picsart.com from any HTTP client.

bash

npm install @picsart/ai-sdk

Authenticate

Send your Picsart API key as a bearer token. The SDK does it for you once the client is created.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY, // sent as: Authorization: Bearer <key>
  apiUrl: 'https://api.picsart.com',
});

python

import os

from picsart_ai_sdk import create_client

ai = create_client(
    api_key=os.environ["PICSART_API_KEY"],  # sent as: Authorization: Bearer <key>
    api_url="https://api.picsart.com",
)

Make a request

Call the model by its id. Over REST, one endpoint serves every model: POST /workflows/v1/models/execute with the model id and its input in the body. The outer params is the envelope every workflow takes; the inner one is this model's input, with the same names generate() takes.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

const result = await ai.generate('minimax-h3-max', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  resolution: "768p",
  duration: 5,
  aspectRatio: "16:9"
});

console.log(result.url); // video URL

python

import asyncio
import os

from picsart_ai_sdk import create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        result = await ai.generate("minimax-h3-max", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "resolution": "768p",
            "duration": 5,
            "aspectRatio": "16:9",
        })

        print(result.url)  # video URL


asyncio.run(main())

bash

curl -X POST 'https://api.picsart.com/workflows/v1/models/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "minimax-h3-max",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "resolution": "768p",
      "duration": 5,
      "aspectRatio": "16:9"
    }
  }
}'

Async (submit & poll)

This model can run longer than the sync limit (~20s). generate() waits for you; to hold on to the job instead, submit it and poll. Over REST, send it to /workflows/v1/models/submit and poll /workflows/v1/models/{taskId}/result until response.status is COMPLETED or FAILED.

import { createClient } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Returns the generation id at once — store it to pick the job up later.
const generationId = await ai.submit('minimax-h3-max', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  resolution: "768p",
  duration: 5,
  aspectRatio: "16:9"
});

// Polls until the job completes; throws if it fails or is cancelled.
const result = await ai.result('minimax-h3-max', generationId);

console.log(result.url); // video URL

python

import asyncio
import os

from picsart_ai_sdk import create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # Returns the generation id at once — store it to pick the job up later.
        generation_id = await ai.submit("minimax-h3-max", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
            "resolution": "768p",
            "duration": 5,
            "aspectRatio": "16:9",
        })

        # Polls until the job completes; raises ApiError if it fails or is cancelled.
        result = await ai.result("minimax-h3-max", generation_id)

        print(result.url)  # video URL


asyncio.run(main())

bash

# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/v1/models/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "model": "minimax-h3-max",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "resolution": "768p",
      "duration": 5,
      "aspectRatio": "16:9"
    }
  }
}'
# → { "status": "success", "response": { "id": "task_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/v1/models/task_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'

Parameters

12 parameters, the same for the SDK and for the inner params over REST. Required ones must be supplied; the rest fall back to their defaults.

Parameter	Type	Required	Default	Details
`prompt` What to make, in plain language: the subject, style, composition and motion. With an input image or video, what to change.	`text`	yes	`—`	max 50000 chars
`startFrame` The first frame, as an image URL. The video starts on this image.	`file (image)`	no	`—`	—
`endFrame` The last frame, as an image URL. The video ends on this image.	`file (image)`	no	`—`	—
`imageUrls` Input images, as URLs: frames to animate, or references for subject, style or composition.	`file (image[])`	no	`—`	—
`videoUrls` Input videos, as URLs.	`file (video[])`	no	`—`	max 15s
`audioUrls` Input audio files, as URLs.	`file (audio[])`	no	`—`	max 15s
`resolution` Output size. Higher costs more and takes longer.	`enum`	no	`768p`	480p, 768p, 1080p
`duration` Length of the output, in seconds.	`range`	no	`5`	5–15 (step 1)
`aspectRatio` Shape of the output as width:height. An auto or adaptive option follows the input image.	`enum`	no	`16:9`	adaptive (follows the input), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
`promptExpansionMode` Whether and how the prompt is expanded before generating.	`enum`	no	`balanced`	disabled, balanced, quality
`seed` Seed for the random generator. The same seed and inputs repeat a result; leave it out for a random one.	`range`	no	`-1`	-1–2147483647
`enableSafetyChecker` Run the vendor's safety check on the result.	`boolean`	no	`true`	—

Response

generate() resolves once the job completes. A video URL. Over REST the output is at response.result, inside the gateway's status envelope with the task id, its status and the amount charged.

json

{
  "items": [
    {
      "url": "https://cdn.picsart.com/…/result"
    }
  ],
  "model": "minimax-h3-max"
}

json

{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result",
      "items": [
        {
          "url": "https://cdn.picsart.com/…/result"
        }
      ],
      "model": "minimax-h3-max"
    }
  }
}

Overview

Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.

That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.

The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.

Make a request

Call the workflow with ai.apis.run() in TypeScript or Python, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.

These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).

import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'minimax/h3-max/video-generation' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('minimax/h3-max/video-generation', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // amount charged, in $

python

import asyncio
import os

from picsart_ai_sdk import ApiRunMode, create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # Calls the 'minimax/h3-max/video-generation' workflow directly — params are sent as-is.
        response = await ai.apis.run("minimax/h3-max/video-generation", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
        }, mode=ApiRunMode.SYNC)

        print(response["result"])  # workflow-specific output
        print((response.get("usage") or {}).get("credits"))  # amount charged, in $


asyncio.run(main())

bash

curl -X POST 'https://api.picsart.com/workflows/minimax/h3-max/video-generation/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "prompt": "A serene mountain lake at golden hour, ultra detailed"
  }
}'

Async (submit & poll)

This model can run longer than the sync limit (~20s). In the SDK, ai.apis.run() with ApiRunMode.ASYNC polls for you; over HTTP, submit and poll yourself.

import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// mode: ASYNC submits the job and polls under the hood — you just await.
const { result } = await ai.apis.run('minimax/h3-max/video-generation', {
  prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.ASYNC,
});

console.log(result);

python

import asyncio
import os

from picsart_ai_sdk import ApiRunMode, create_client


async def main() -> None:
    async with create_client(
        api_key=os.environ["PICSART_API_KEY"],
        api_url="https://api.picsart.com",
    ) as ai:
        # mode=ASYNC submits the job and polls under the hood — you just await.
        response = await ai.apis.run("minimax/h3-max/video-generation", {
            "prompt": "A serene mountain lake at golden hour, ultra detailed",
        }, mode=ApiRunMode.ASYNC)

        print(response["result"])


asyncio.run(main())

bash

# 1. Submit the job
curl -X POST 'https://api.picsart.com/workflows/minimax/h3-max/video-generation/submit' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "prompt": "A serene mountain lake at golden hour, ultra detailed"
  }
}'
# → { "status": "success", "response": { "id": "wf_abc123" } }

# 2. Poll until response.status is COMPLETED
curl 'https://api.picsart.com/workflows/minimax/h3-max/video-generation/wf_abc123/result' \
  -H 'Authorization: Bearer $PICSART_API_KEY'

Parameters

13 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.

Parameter	Type	Required	Default	Details
`prompt` Text prompt for video generation. With reference inputs, address them by modality and order — Image 1, Image 2, Video 1, Audio 1, and so on.	`string`	yes	`—`	max 50000 chars
`prompt_expansion_mode` How much effort to spend rewriting the prompt before generation. 'disabled' skips it, 'balanced' returns in about a second, 'quality' spends up to ~30s on a richer prompt.	`string`	no	`balanced`	`disabledbalancedquality`
`duration` Video duration in seconds	`number`	no	`5`	5–15
`resolution` The native generation resolution of the video, or 1080P latent refinement from a native 768P source. Case-insensitive.	`string`	no	`768P`	`480P768P1080P`
`aspect_ratio` The aspect ratio of the generated video. Omitted, it defaults to 16:9 generating from the prompt alone and to 'adaptive' generating from references. Ignored when a frame is supplied — the output then follows that image. 'adaptive' follows the reference inputs, so it is accepted only alongside them.	`string`	no	`—`	`adaptive21:916:94:31:13:49:16`
`image_url` URL of the image to use as the first frame. When provided, the output canvas follows this image. Cannot be combined with reference inputs.	`string`	no	`—`	—
`end_image_url` URL of the image to use as the last frame. It may be provided alone for end-only keyframe generation, in which case the output canvas follows this image. Cannot be combined with reference inputs.	`string`	no	`—`	—
`reference_image_urls` URLs of subject/style reference images, referenced in the prompt as Image 1, Image 2, and so on. Reference images, videos and audio clips must add up to at most 12 files. Cannot be combined with frames.	`string[]`	no	`—`	max 9 items
`reference_video_urls` URLs of motion/reference video clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Video 1, Video 2, and so on. Reference images, videos and audio clips must add up to at most 12 files. Cannot be combined with frames.	`string[]`	no	`—`	max 3 items
`reference_audio_urls` URLs of reference audio clips (2-15 seconds each, combined duration at most 15 seconds), referenced in the prompt as Audio 1, Audio 2, and so on. Needs at least one reference image or video alongside it.	`string[]`	no	`—`	max 3 items
`seed` Random seed. A random seed is selected when omitted.	`number`	no	`—`	—
`enable_safety_checker` Run the vendor safety checker	`boolean`	no	`true`	—
`options` GenAI options (safety checks, Picsart Drive)	`object`	no	`—`	—
└`safety_checks` Safety check settings	`object`	no	`—`	—
└`enabled` Whether to run content moderation. Defaults to true.	`boolean`	no	`—`	—
└`drive` Save result to Picsart Drive	`object`	no	`—`	—
└`name` File name in Picsart Drive	`string`	yes	`—`	—
└`attributes` Custom attributes to attach to the file	`object`	no	`—`	—
└`folder` Target folder in Picsart Drive	`object`	no	`—`	—
└`inputs_transformation` Input transformation settings	`object`	no	`—`	—
└`downscale_oversized_images` Whether to downscale oversized input images. Defaults to false.	`boolean`	no	`—`	—

Response

Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the result itself is the vendor's own shape.

json

{
  "result": {
    "url": "https://cdn.picsart.com/…/result.mp4",
    "mimeType": "video/mp4",
    "expandedPrompt": "…",
    "driveFile": {
      "id": "wf_abc123"
    }
  }
}

json

{
  "status": "success",
  "response": {
    "id": "wf_abc123",
    "status": "COMPLETED",
    "result": {
      "url": "https://cdn.picsart.com/…/result.mp4",
      "mimeType": "video/mp4",
      "expandedPrompt": "…",
      "driveFile": {
        "id": "wf_abc123"
      }
    }
  }
}

Rates

What this model costs per generation, in USD. Every row is an exact rate — the columns are the settings that change it.

Tier	Use case	Rate
480p	Image → video, Text → video	$0.03 / sec
768p	Image → video, Text → video	$0.048 / sec
480p	Video → video	$0.05 / sec
768p	Video → video	$0.08 / sec
1080p	Image → video, Text → video	$0.096 / sec
1080p	Video → video	$0.16 / sec

MiniMaxMiniMax H3 Max API

Params

Result

Other models from MiniMax

Install the SDK

Authenticate

Make a request

Async (submit & poll)

Parameters

Response

Overview

Make a request

Async (submit & poll)

Parameters

Response

Rates