Name: Image-to-Video API (Wan 2.2 A14B)
Brand: magicapi
SKU: api-magicapi-image-to-video-api-wan-video-wan-2-2-i2v-a14b
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎥 Image-to-Video API (Wan 2.2 A14B)

## Overview
The Image-to-Video API runs Wan 2.2 A14B, an image-to-video model from Wan (Alibaba). You send a still image and a text prompt describing the motion, and the model returns a short MP4 video generated from your image.

Output is available at 480p (default) or 720p. At 480p, 832x480 corresponds to a 16:9 aspect ratio and 480x832 to 9:16.

## Features
- Animates a still image (`image`) according to a text prompt (`prompt`).
- Two resolutions: `480p` (default) and `720p`.
- Control over length and motion with `num_frames` (81 to 100, default 81) and `frames_per_second` (5 to 24, default 16).
- Quality and speed controls: `sample_steps` (1 to 50, default 40), `sample_shift` (1 to 20, default 5) and `go_fast`.
- Optional `seed` (leave blank for a random seed).
- Flat price per output video, set by the resolution.

## Use Cases
1. **Product and marketing clips**  
   Turn a product photo or campaign image into a short moving shot.

2. **Social media posts**  
   Add motion to still photos or artwork for short video posts.

3. **Storyboards and previews**  
   Quickly see how a frame might move before committing to a full production.

4. **Illustration and concept art**  
   Bring a character or scene illustration to life with a short camera or subject movement.

## Visual Examples
This is a real request sent through api.market.

**Input image:**

![Input image: a woman in a yellow raincoat on a rainy street at night under a pink api.market neon sign](https://blog.api.market/wp-content/uploads/2026/09/kling-v2-1-input-api-market.webp)

**Prompt:** "Rain keeps falling as she turns toward the camera"

**Settings:** `resolution: "480p"`. All other fields used their defaults.

**Output video:** [Watch the example video](https://blog.api.market/wp-content/uploads/2026/10/wan-2.2-i2v-a14b-output-api-market.mp4)

## Pricing
- Price: $0.01 per API unit.
- You are billed per output video. The number of units depends only on the resolution.
- `resolution: "480p"` (the default): 50 units per video, which is $0.50 per video.
- `resolution: "720p"`: 125 units per video, which is $1.25 per video.
- `num_frames`, `frames_per_second`, `sample_steps`, `sample_shift`, `go_fast` and `seed` do not change the price.
- Failed or canceled predictions are not billed.
- GET requests to check prediction status are free and don't count toward API unit usage.
- No monthly subscription fee. Pay As You Go (PAYG): you only pay for what you use.

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
This API is asynchronous:
1. POST `/predictions` with a `version` and an `input` object. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` (for example once per second) while the status is `starting` or `processing`.
3. Stop when the status is `succeeded` (the `output` field holds the video URL), `failed` or `canceled` (the `error` field explains why).

Video jobs can take several minutes, so allow a generous client timeout (the examples below use 10 minutes).

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
  "version": "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9",
  "input": {
    "prompt": "Rain keeps falling as she turns toward the camera",
    "image": "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-1-input-api-market.webp",
    "resolution": "480p"
  }
}'
```

Response (201 Created):
```json
{
  "id": "ufawqhfynnddngldkgtslldrkq",
  "version": "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9",
  "status": "starting",
  "created_at": "2026-10-13T10:37:01.920Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when finished (200 OK):
```json
{
  "id": "ufawqhfynnddngldkgtslldrkq",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/wan-2.2-i2v-a14b-output-api-market.mp4",
  "created_at": "2026-10-13T10:37:01.920Z",
  "started_at": "2026-10-13T10:37:03.112Z",
  "completed_at": "2026-10-13T10:39:12.480Z"
}
```

### Status Codes
- 200 OK: prediction status returned.
- 201 Created: prediction created; poll it for the result. This is a success response.
- 400 Bad Request: invalid or missing input fields.
- 401 Unauthorized: missing or invalid API key.
- 404 Not Found: no prediction with that id.
- 429 Too Many Requests: rate limit exceeded; wait and retry.
- 500 Internal Server Error or 503 Service Unavailable: temporary server problem; retry with backoff.

### Error Handling
- Treat both 200 and 201 as success on the create call.
- A prediction can be accepted (201) and still end with `status: "failed"`. Read the `error` field in that case; failed predictions are not billed.
- Retry 429 and 5xx responses with exponential backoff. Do not retry 400 or 401 without fixing the request or key.

## Rate Limits

All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Implementation Guide

### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b";

async function runPrediction(input) {
  const create = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: { "Content-Type": "application/json", "x-api-market-key": apiKey },
    body: JSON.stringify({ version: "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9", input })
  });
  if (create.status !== 200 && create.status !== 201) {
    throw new Error(`API error: ${create.status} ${await create.text()}`);
  }
  const { id } = await create.json();

  const deadline = Date.now() + 600000; // 10 minutes
  while (Date.now() < deadline) {
    const res = await fetch(`${baseUrl}/predictions/${id}`, { headers: { "x-api-market-key": apiKey } });
    if (!res.ok) throw new Error(`API error: ${res.status} ${await res.text()}`);
    const prediction = await res.json();
    if (prediction.status === "succeeded") return prediction.output;
    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "unknown error"}`);
    }
    await new Promise((r) => setTimeout(r, 1000));
  }
  throw new Error("Prediction timed out after 10 minutes");
}

runPrediction({
  "prompt": "Rain keeps falling as she turns toward the camera",
  "image": "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-1-input-api-market.webp",
  "resolution": "480p"
}).then((output) => console.log(output));
```

### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b"

def run_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    create = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9", "input": input_data},
    )
    if create.status_code not in (200, 201):
        raise Exception(f"API error: {create.status_code} {create.text}")
    prediction_id = create.json()["id"]

    deadline = time.time() + 600  # 10 minutes
    while time.time() < deadline:
        res = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers={"x-api-market-key": API_KEY})
        if res.status_code != 200:
            raise Exception(f"API error: {res.status_code} {res.text}")
        prediction = res.json()
        if prediction["status"] == "succeeded":
            return prediction["output"]
        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'unknown error'}")
        time.sleep(1)
    raise Exception("Prediction timed out after 10 minutes")

print(run_prediction({
  "prompt": "Rain keeps falling as she turns toward the camera",
  "image": "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-1-input-api-market.webp",
  "resolution": "480p"
}))
```

### cURL
```bash
# Step 1: create the prediction (returns 201 Created with an id)
curl -X POST "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
  "version": "2c62e0842338726c74ad99a3c469255ce3f4c1f66ee000c265451b87754ac0c9",
  "input": {
    "prompt": "Rain keeps falling as she turns toward the camera",
    "image": "https://blog.api.market/wp-content/uploads/2026/09/kling-v2-1-input-api-market.webp",
    "resolution": "480p"
  }
}'

# Step 2: poll until status is succeeded, failed or canceled (replace PREDICTION_ID)
curl -X GET "https://prod.api.market/api/v1/magicapi/image-to-video-api-wan-video-wan-2-2-i2v-a14b/predictions/PREDICTION_ID" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

## Input Parameters
| Parameter | Type | Required | Default | Allowed values | Description |
|-----------|------|----------|---------|----------------|-------------|
| `prompt` | string | Yes | none | - | Prompt for video generation |
| `image` | string (URL) | No | none | - | Input image to generate video from. |
| `go_fast` | boolean | No | `false` | - | Go fast |
| `num_frames` | integer | No | `81` | 81 to 100 | Number of video frames. 81 frames give the best results |
| `resolution` | string | No | `"480p"` | `"480p"`, `"720p"` | Resolution of video. 832x480px corresponds to 16:9 aspect ratio, and 480x832px is 9:16 |
| `frames_per_second` | integer | No | `16` | 5 to 24 | Frames per second of the output video. On api.market the price is per output video and does not depend on the frame rate. |
| `sample_steps` | integer | No | `40` | 1 to 50 | Number of generation steps. Fewer steps means faster generation, at the expense of output quality. 30 steps is sufficient for most prompts |
| `sample_shift` | number | No | `5` | 1 to 20 | Sample shift factor |
| `seed` | integer | No | none | - | Random seed. Leave blank for random |

Only `prompt` is marked required in the model's schema. This is an image-to-video model, so send an `image` to generate the video from.

## Output
A single URL (string) pointing to the generated MP4 video.

## FAQ
1. **How long is the output video?**  
   Length is `num_frames` divided by `frames_per_second`. With the defaults (81 frames at 16 frames per second) that is about 5 seconds.

2. **Does a longer video cost more?**  
   No. The price is per video: $0.50 at 480p and $1.25 at 720p, whatever `num_frames` or `frames_per_second` you choose.

3. **Which aspect ratios are supported?**  
   The schema describes 832x480 as 16:9 and 480x832 as 9:16 at 480p.

4. **How can I make generation faster?**  
   Lower `sample_steps` (30 is enough for most prompts) or set `go_fast: true`. Fewer steps can reduce quality.

## Contact Us

If you have any questions or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Animate a still image with a text prompt using Wan 2.2 A14B. 480p or 720p output, priced per video, pay as you go with no subscription.