# MiniMax H3 Context IR

> MiniMax H3 Context IR — enhances a video prompt from text plus optional first/last frame, reference images, videos, and audio. Returns an enhanced prompt, not a video.

## Overview

- **Model ID**: `minimax-h3-context-ir`
- **Workflow**: `minimax/v2/h3-context-ir`
- **Provider**: MiniMax
- **Category**: Video → Text (text)
- **Output**: Generated text.
- **Tags**: new, vision, video input, audio input, start/end frame
- **Unified endpoint**: `POST https://api.picsart.com/workflows/v1/models/execute` (model id in the body)
- **Compatibility endpoint**: `POST https://api.picsart.com/workflows/minimax/v2/h3-context-ir/execute` (vendor's own parameters)
- **Execution**: sync (`/execute`) returns the result in one call; async is also available
- **Model page**: https://picsart.com/api-platform/models/minimax-h3-context-ir

## Pricing

Rates are in USD. Every row below is an exact rate for the settings it names — the columns are the settings that change the price for this model. Every response reports what was actually charged in `response.usage.credits`.

| Tier | Rate |
| --- | --- |
| Input | $0.45 / 1M input tokens |
| Output text | $1.80 / 1M output text tokens |

Published rates. Volume pricing, invoicing and annual agreements: https://picsart.com/api-platform/contact-sales

## Authentication

The SDK and the REST API authenticate with a Picsart API key sent as a bearer token. Create a key in the console at https://picsart.com/api-platform/dashboard/api-keys, keep it in a server-side environment variable, and never ship it in browser code or commit it.

```bash
export PICSART_API_KEY="YOUR_KEY"
```

```http
Authorization: Bearer $PICSART_API_KEY
```

The CLI and the MCP server do not use an API key: `gen-ai login` signs in through the browser once per machine and stores a token locally.

## Interfaces

- **SDK** — `@picsart/ai-sdk` (TypeScript, Node 20+, ESM). Type-safe `ai.generate()` / `ai.generateText()` with per-model parameter types; polls long jobs for you.
- **REST** — the API gateway at `https://api.picsart.com`. Sync `/execute`, or async `/submit` + `/{taskId}/result`.
- **CLI** — `@picsart/gen-ai` (`gen-ai`). Generate from a terminal, quote cost before spending, emit JSON for pipelines.
- **MCP** — the same models inside Claude Code, Cursor, Windsurf and other MCP hosts. Setup: https://picsart.com/gen-ai-mcp/

```bash
npm install @picsart/ai-sdk      # SDK
npm install -g @picsart/gen-ai   # CLI (also drives the MCP server)
```

## Unified API (recommended)

One parameter set, used by the SDK and by REST alike: the names below are what `ai.generate('minimax-h3-context-ir', …)` takes, and what goes inside the inner `params` of a REST call. Over REST the model id travels in the body, not the path — one workflow, `v1/models`, fronts the whole catalogue.

### Execution modes

- **Sync** — `POST /workflows/v1/models/execute` returns the result in one call. Only for jobs that finish within ~20 seconds; otherwise it times out.
- **Async** — `POST /workflows/v1/models/submit` returns a task id; poll `GET /workflows/v1/models/{taskId}/result` until `response.status` is `COMPLETED` or `FAILED`. Task statuses: `ACCEPTED` · `IN_PROGRESS` · `COMPLETED` · `FAILED`.
- **SDK** — `ai.generate()` always awaits the finished result; polling is hidden.

### Input parameters

- **`prompt`** (`string`, _required_): Prompt
- **`startFrame`** (`string`, _optional_): Start Frame
  - Accepts: image URL
- **`endFrame`** (`string`, _optional_): End Frame
  - Accepts: image URL
- **`imageUrls`** (`list<string>`, _optional_): Reference Images
  - Accepts: image URLs (max 9)
- **`videoUrls`** (`list<string>`, _optional_): Reference Videos
  - Accepts: video URLs (max 3)
- **`audioUrls`** (`list<string>`, _optional_): Reference Audios
  - Accepts: audio URLs (max 3)
- **`duration`** (`number`, _optional_)
  - Default: `5`
  - Range: 4–15 (step 1)
- **`aspectRatio`** (`string`, _optional_)
  - Default: `"adaptive"`
  - Options: `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`

### Input JSON Schema

The inner `params` object. Over REST it is wrapped as `{ "params": { "model": "<id>", "params": <this> } }`; the SDK takes it directly.

```json
{
  "type": "object",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Prompt"
    },
    "startFrame": {
      "type": "string",
      "format": "uri",
      "description": "Start Frame"
    },
    "endFrame": {
      "type": "string",
      "format": "uri",
      "description": "End Frame"
    },
    "imageUrls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri",
        "description": "image URL"
      },
      "maxItems": 9,
      "description": "Reference Images"
    },
    "videoUrls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri",
        "description": "video URL"
      },
      "maxItems": 3,
      "description": "Reference Videos"
    },
    "audioUrls": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "uri",
        "description": "audio URL"
      },
      "maxItems": 3,
      "description": "Reference Audios"
    },
    "duration": {
      "type": "number",
      "minimum": 4,
      "maximum": 15,
      "multipleOf": 1,
      "default": 5
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "adaptive",
        "21:9",
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16"
      ],
      "default": "adaptive"
    }
  },
  "additionalProperties": false
}
```

### Required parameters example

The required parameters plus the defaults that shape the output, as a REST body:

```json
{
  "params": {
    "model": "minimax-h3-context-ir",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "duration": 5,
      "aspectRatio": "adaptive"
    }
  }
}
```

### Response

The body is the gateway's status envelope: the output is at `response.result`, next to the task id, its status and the credits charged. Text models return `text`.

```json
{
  "status": "success",
  "response": {
    "id": "task_abc123",
    "status": "COMPLETED",
    "result": {
      "text": "…generated text…",
      "model": "minimax-h3-context-ir"
    }
  }
}
```

What `ai.generate()` / `ai.generateText()` resolve to (the envelope already unwrapped):

```json
{
  "text": "…generated text…",
  "model": "minimax-h3-context-ir"
}
```

### Usage examples

#### TypeScript (SDK)

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

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

const { text } = await ai.generateText('minimax-h3-context-ir', {
  prompt: "A serene mountain lake at golden hour, ultra detailed",
  duration: 5,
  aspectRatio: "adaptive"
});

console.log(text);
```

#### cURL (sync)

```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-context-ir",
    "params": {
      "prompt": "A serene mountain lake at golden hour, ultra detailed",
      "duration": 5,
      "aspectRatio": "adaptive"
    }
  }
}'
```

#### CLI

```bash
gen-ai login  # once per machine
gen-ai models info minimax-h3-context-ir  # this model's parameters
gen-ai pricing minimax-h3-context-ir  # quote before spending credits
gen-ai generate -m minimax-h3-context-ir \
  -p "A serene mountain lake at golden hour" \
  -d 5 \
  --ar adaptive
```

## Compatibility API (vendor parameters)

Alongside the unified API, the `minimax/v2/h3-context-ir` workflow takes MiniMax's own parameters exactly as the vendor defines them — nothing renamed or reshaped. It is the shortest path onto Picsart for request bodies already written against the vendor; the trade is that a request is written for one vendor, and the result comes back in the vendor's own shape. Same authentication.

- **Endpoint**: `POST https://api.picsart.com/workflows/minimax/v2/h3-context-ir/execute` (sync) · `POST …/submit` + `GET …/{taskId}/result` (async)
- **SDK**: `ai.apis.run('minimax/v2/h3-context-ir', params, { mode })` — params forwarded verbatim

### Vendor parameters

| Parameter | Type | Required | Default | Details |
| --- | --- | --- | --- | --- |
| `model` | `string` | no | `MiniMax-H3` | Model id · Options: `MiniMax-H3` |
| `content` | `MinimaxContentItem[]` | yes | — | Content items. Must contain one non-empty text item. Add image/video/audio items with a role to provide first-frame, first-to-last keyframe, or multimodal reference context for the enhancement. Frame and reference roles are mutually exclusive. |
| └ `type` | `string` | yes | — | Media type of this content item · Options: `text`, `image_url`, `video_url`, `audio_url` |
| └ `text` | `string` | no | — | Text prompt; required for a `text` item |
| └ `image_url` | `object` | no | — | Image URL for an `image_url` item |
| └   `url` | `string` | yes | — | Publicly reachable URL, an mm_file://{file_id} handle, or a data: URI (small assets only) |
| └ `video_url` | `object` | no | — | Video URL for a `video_url` item |
| └   `url` | `string` | yes | — | Publicly reachable URL, an mm_file://{file_id} handle, or a data: URI (small assets only) |
| └ `audio_url` | `object` | no | — | Audio URL for an `audio_url` item |
| └   `url` | `string` | yes | — | Publicly reachable URL, an mm_file://{file_id} handle, or a data: URI (small assets only) |
| └ `role` | `string` | no | — | Role of a media item; omit for text · Options: `first_frame`, `last_frame`, `reference_image`, `reference_video`, `reference_audio` |
| `duration` | `number` | yes | `5` | Target video duration in seconds (4–15); informs the enhanced prompt · 4–15 |
| `ratio` | `string` | no | — | Target aspect ratio; informs the enhanced prompt. Defaults to adaptive when omitted. · Options: `adaptive`, `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` |
| `callback_url` | `string` | no | — | Webhook URL to receive task state changes after challenge verification |
| `options` | `object` | no | — | GenAI options (safety checks) |
| └ `safety_checks` | `object` | no | — | Safety check settings |
| └   `enabled` | `boolean` | no | — | Whether to run content moderation. Defaults to true. |
| └ `drive` | `object` | no | — | Save result to Picsart Drive |
| └   `name` | `string` | yes | — | File name in Picsart Drive |
| └   `attributes` | `object` | no | — | Custom attributes to attach to the file |
| └   `folder` | `object` | no | — | Target folder in Picsart Drive |
| └ `inputs_transformation` | `object` | no | — | Input transformation settings |
| └   `downscale_oversized_images` | `boolean` | no | — | Whether to downscale oversized input images. Defaults to false. |

### Example request body

```json
{
  "params": {
    "content": [
      {
        "type": "text"
      }
    ],
    "duration": 5
  }
}
```

### Usage examples

#### TypeScript (`ai.apis.run`)

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

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

// Calls the 'minimax/v2/h3-context-ir' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('minimax/v2/h3-context-ir', {
  content: [
    {
      type: "text"
    }
  ],
  duration: 5
}, {
  mode: ApiRunMode.SYNC,
});

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

#### cURL (sync)

```bash
curl -X POST 'https://api.picsart.com/workflows/minimax/v2/h3-context-ir/execute' \
  -H 'Authorization: Bearer $PICSART_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "params": {
    "content": [
      {
        "type": "text"
      }
    ],
    "duration": 5
  }
}'
```

### Response

Over HTTP the vendor-shaped result arrives inside the gateway envelope at `response.result`:

```json
{
  "status": "success",
  "response": {
    "id": "wf_abc123",
    "status": "COMPLETED",
    "result": {
      "prompt": "…",
      "usage": {
        "total_tokens": 0,
        "prompt_tokens": 0,
        "completion_tokens": 0
      }
    }
  }
}
```

`ai.apis.run()` unwraps that envelope and resolves to `{ result, usage }`:

```json
{
  "result": {
    "prompt": "…",
    "usage": {
      "total_tokens": 0,
      "prompt_tokens": 0,
      "completion_tokens": 0
    }
  }
}
```

## Additional resources

- Model page: https://picsart.com/api-platform/models/minimax-h3-context-ir
- Try it: https://picsart.com/api-platform/models/minimax-h3-context-ir/playground
- SDK: https://picsart.com/api-platform/models/minimax-h3-context-ir/sdk
- REST API (unified): https://picsart.com/api-platform/models/minimax-h3-context-ir/api
- Compatibility API (vendor parameters): https://picsart.com/api-platform/models/minimax-h3-context-ir/advanced
- Pricing: https://picsart.com/api-platform/models/minimax-h3-context-ir/pricing
- This document: https://picsart.com/api-platform/models/minimax-h3-context-ir/llms.txt
- All models: https://picsart.com/api-platform/models
- Docs — quickstart https://picsart.com/api-platform/docs/quickstart, authentication https://picsart.com/api-platform/docs/authentication, SDK https://picsart.com/api-platform/docs/sdk, REST https://picsart.com/api-platform/docs/api-reference, CLI https://picsart.com/api-platform/docs/cli, MCP https://picsart.com/api-platform/docs/mcp
- CLI reference: https://picsart.github.io/picsart-mcp-cli-docs/guide/introduction