# Hailuo 02 i2v Pro — Atlas Cloud API

> Hailuo 02 is a new AI video generation model from Hailuo AI.

This is the machine-readable API reference for **Hailuo 02 i2v Pro** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `minimax/hailuo-02/i2v-pro`
- **Built by**: MiniMax
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/minimax/hailuo-02/i2v-pro
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.49 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

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

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "minimax/hailuo-02/i2v-pro"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video minimax/hailuo-02/i2v-pro -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **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/hailuo-02/i2v-pro`


## 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/hailuo-02/i2v-pro"`

- **`prompt`** (`string`, _optional_):
  Generate a description of the video.(Note: Maximum support 2000 characters).
  - Default: `"The boxer in the image throws fast punches in a gritty underground gym, bobbing and weaving, sweat flying, dramatic lighting with dust in the air, camera circles around with intense close-ups"`

- **`image`** (`string`, _required_):
  The model generates video with the picture passed in as the first frame.Base64 encoded strings in data:image/jpeg; base64,{data} format for incoming images, or URLs accessible via the public network. The uploaded image needs to meet the following conditions: Format is JPG/JPEG/PNG; The aspect ratio is greater than 2:5 and less than 5:2; Short side pixels greater than 300px; The image file size cannot exceed 20MB.
  - Default: `"https://static.atlascloud.ai/media/images/1751885591673251332_d8mieaOL.jpeg"`

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  The model automatically optimizes incoming prompts to enhance output quality. This also activates the safety checker, which ensures content safety by detecting and filtering potential risks.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "minimax/hailuo-02/i2v-pro",
  "image": "https://static.atlascloud.ai/media/images/1751885591673251332_d8mieaOL.jpeg"
}
```


**Full Example**:

```json
{
  "model": "minimax/hailuo-02/i2v-pro",
  "prompt": "The boxer in the image throws fast punches in a gritty underground gym, bobbing and weaving, sweat flying, dramatic lighting with dust in the air, camera circles around with intense close-ups",
  "image": "https://static.atlascloud.ai/media/images/1751885591673251332_d8mieaOL.jpeg",
  "enable_prompt_expansion": false
}
```


### Output Schema

The API returns the following output format:


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

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

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

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

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

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

- **`has_nsfw_contents`** (`array[boolean]`, _optional_):
  Array of boolean values indicating NSFW detection for each output.



**Example Response**:

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


## 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/hailuo-02/i2v-pro",
  "prompt": "The boxer in the image throws fast punches in a gritty underground gym, bobbing and weaving, sweat flying, dramatic lighting with dust in the air, camera circles around with intense close-ups",
  "image": "https://static.atlascloud.ai/media/images/1751885591673251332_d8mieaOL.jpeg",
  "enable_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/hailuo-02/i2v-pro)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

### What Makes Hailuo 02 Outperform Other AI Video Generation Models?

#### 1080P Native Output
Nobody wants blurry footage. Hailuo 02 gives you the full HD 1080P video straight from the model, not upscaled afterwards. This is a huge leap from the previously limited 720P. Your video will look sharp even on those big screens. Ads, explainers, shorts—it all matters if it looks clear. And Hailuo 02 can deliver that clarity with just a few clicks.

#### Multiple Duration Options
Flexibility means a lot with AI video generation, and Hailuo 02 offers clip format in both 6-second and 10-second formats. Creators can mix and match formats seamlessly, and the length of content becomes more controllable without impacting quality. It's a small detail but has a big impact on workflow. There’s no need to re-render full scenes when mocking up combinations—just generate and combine.

#### Enhanced Motion & Physical Effects
This model doesn’t merely understand movement—it completely owns it. Hailuo 02 is equipped with state-of-the-art motion rendering, allowing it to capture dynamic scenes and physical interactions more smoothly than most competitors. It adapts easily to prompts involving complex physics, such as flying debris, bouncing objects, or camera shakes. The result: videos that feel organic and cinematic.

#### Better Scene Transitions
Image-to-video models can sometimes produce awkward cuts or uneven frame stitching, but Hailuo 02 really smooths things out. Transitions between frames resemble real-world camera work more than simple machine stitching. The end result is closer to a movie trailer than a slideshow, especially for creators transforming still images into dynamic sequences.

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/minimax/hailuo-02/i2v-pro · Docs: https://www.atlascloud.ai/docs