> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gmicloud.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# wan3.0-video

> API usage guide for wan3.0-video.

**Model ID**

```bash theme={null}
wan3.0-video
```

**Calling method:** async

# wan3.0-video API Usage Guide

## Overview

**wan3.0-video** is Wan AI's Wan 3.0 video model. Unlike the wan2.x line, which splits text-to-video, image-to-video and reference-to-video across separate model IDs, Wan 3.0 is a **single unified model**: the task type is determined by what you put in the media inputs, not by which endpoint you call.

Capabilities:

* **Text-to-video** — prompt only
* **Image-to-video** — supply `first_frame`, optionally `last_frame`
* **Reference-to-video** — supply `reference_image` (up to 10) and/or `reference_video` (up to 5)
* **Video editing / continuation** — supply `video`
* **Duration up to 30 seconds** in a single generation (wan2.x caps at 15)
* **Audio generated by default** — every output carries an audio track
* **Adaptive aspect ratio** — `ratio: "adaptive"` derives the output framing from the input media

Requests are submitted to the request-queue API and results are retrieved via polling.

## Authentication

All API requests require authentication using an API key. Include your API key in the Authorization header:

```bash theme={null}
Authorization: Bearer YOUR_API_KEY
```

## Submit Video Generation Request

### Base URL

```
https://console.gmicloud.ai
```

### Endpoint

```
POST /api/v1/ie/requestqueue/apikey/requests
```

### Text-to-video

```bash theme={null}
curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "payload": {
      "prompt": "A drone shot gliding over a misty forest at sunrise, golden light breaking through the canopy",
      "negative_prompt": "blurry, low quality, distorted",
      "resolution": "1080P",
      "ratio": "16:9",
      "duration": 10,
      "prompt_extend": true,
      "watermark": false,
      "seed": 12345
    }
  }'
```

### Image-to-video

Supply `first_frame`. Use `ratio: "adaptive"` to let the output framing follow the input image instead of being forced to 16:9.

```bash theme={null}
curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "payload": {
      "prompt": "The camera slowly pushes in as the city lights begin to flicker on",
      "first_frame": "https://example.com/first.png",
      "resolution": "720P",
      "ratio": "adaptive",
      "duration": 5
    }
  }'
```

### Reference-to-video

```bash theme={null}
curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan3.0-video",
    "payload": {
      "prompt": "The same character walking through a night market",
      "reference_image": ["https://example.com/ref1.png", "https://example.com/ref2.png"],
      "resolution": "720P",
      "duration": 8
    }
  }'
```

### Request Parameters

| Parameter | Type | Required | Description | Default | Constraints |
| - | - | - | - | - | - |
| `prompt` | string | Yes | Text prompt describing the desired video | - | Max 5000 characters |
| `negative_prompt` | string | No | What to avoid in the video | "" | Max 500 characters |
| `first_frame` | string (URL) | No | Image used as the first frame (image-to-video) | null | Public HTTP(S) URL |
| `last_frame` | string (URL) | No | Image used as the last frame | null | Public HTTP(S) URL |
| `reference_image` | string or array | No | Reference image(s) for subject/style consistency | null | Up to 10 |
| `reference_video` | string or array | No | Reference video(s) | null | Up to 5 |
| `video` | string (URL) | No | Input video for editing / continuation | null | Input + output duration must total 30 seconds or less |
| `audio_url` | string (URL) | No | Audio used to drive the generated video | null | wav/mp3 |
| `resolution` | string (enum) | No | Output resolution tier | "1080P" | `"480P"`, `"720P"`, `"1080P"` — **uppercase `P` required** |
| `ratio` | string (enum) | No | Aspect ratio | "adaptive" | `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`, `"adaptive"` |
| `duration` | integer | No | Video length in seconds | 5 | 2-30 |
| `prompt_extend` | boolean | No | Let an LLM rewrite the prompt for richer detail | true | - |
| `watermark` | boolean | No | Add a fixed `AI Generated` watermark | false | - |
| `seed` | integer | No | Random seed | - | 0-2147483647 |

> **`resolution` is case-sensitive.** The upstream model accepts `"480P"`, `"720P"` and `"1080P"` only. A lowercase value such as `"720p"` is rejected and the request fails with `Input should be '1080P', '720P' or '480P': parameters.resolution`. The failure is fast (about one second) and the request is refunded automatically, but it will not silently fall back to a working value.

> **At least one of `prompt` or a media input is required.** Sending neither fails with `prompt and media cannot both be empty`.

### Response

```json theme={null}
{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "model": "wan3.0-video",
  "status": "queued",
  "created_at": 1786561117,
  "updated_at": 1786561117,
  "queued_at": 1786561117
}
```

## Check Request Status

### Endpoint

```
GET /api/v1/ie/requestqueue/apikey/requests/{request_id}
```

### Example

```bash theme={null}
curl -X GET "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests/550e8400-e29b-41d4-a716-446655440000" \
  -H "Authorization: Bearer YOUR_API_KEY"
```

### Response

```json theme={null}
{
  "request_id": "550e8400-e29b-41d4-a716-446655440000",
  "org_id": "your-org-id",
  "model": "wan3.0-video",
  "status": "success",
  "is_public": false,
  "payload": {
    "prompt": "A drone shot gliding over a misty forest at sunrise",
    "resolution": "1080P",
    "ratio": "16:9",
    "duration": 10
  },
  "outcome": {
    "media_urls": [
      {"id": "0", "url": "https://storage.googleapis.com/bucket/generated-video.mp4"}
    ],
    "thumbnail_image_url": "https://storage.googleapis.com/bucket/thumbnail.jpg"
  },
  "created_at": 1786561117,
  "updated_at": 1786561405,
  "queued_at": 1786561117
}
```

## Request Status Values

| Status | Description |
| - | - |
| `queued` | Request is waiting to be processed |
| `processing` | Video generation is in progress |
| `success` | Video generation completed successfully |
| `failed` | Video generation failed (the request is refunded) |
| `cancelled` | Request was cancelled |

## Pricing

Billed per second of successfully generated video, by resolution tier. Failed generations are not billed.

| Resolution | Price |
| - | - |
| 480P | \$0.05 / second |
| 720P | \$0.10 / second |
| 1080P | \$0.20 / second |

A 30-second 1080P generation therefore costs \$6.00. Keep this in mind before combining the maximum duration with the highest resolution.

## List Your Requests

### Endpoint

```
GET /api/v1/ie/requestqueue/apikey/requests?model_id=wan3.0-video
```

## List Available Models

### Endpoint

```
GET /api/v1/apikey/models
```

## Tips for Better Results

1. **Detailed prompts**: describe motion, camera movement, lighting and atmosphere explicitly
2. **Prompt extension**: keep `prompt_extend` enabled for short prompts to let the model enrich them
3. **Negative prompts**: exclude common artifacts such as "blurry, low quality, deformed, extra fingers"
4. **Use `adaptive` for media-driven jobs**: with an input image or video, `ratio: "adaptive"` preserves the source framing; with a text-only prompt it behaves the same as `16:9`
5. **Long-form**: the 2-30 second range covers a full shot in one generation, but cost scales linearly with duration
6. **Audio**: outputs include a generated audio track by default; supply `audio_url` when you need the motion to follow specific audio
7. **Uppercase resolution**: always send `480P` / `720P` / `1080P`, never lowercase


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.