# Qwen Wan 2.5 — Text To Video

> Call the Wan 2.5 API on GPTProto: Alibaba's text-to-video model with native synchronized audio, up to 1080p and 10s. From $0.225/run on one balance across 200+ models. See pricing, prompts, and Wan 2.5 vs Sora 2.

## Overview

- **Endpoint**: `POST https://gptproto.com/api/v3/alibaba/wan-2.5/text-to-video`
- **Result URL**: `GET https://gptproto.com/api/v3/predictions/{result_id}/result` — the submit response also returns the authoritative URL in `data.urls.get`
- **Model ID**: `wan-2.5`
- **Vendor**: Qwen
- **Scene**: `text-to-video`
- **Category**: text-to-video
- **Modalities**: input text → output video
- **Playground**: https://gptproto.com/model/qwen/wan-2.5/text-to-video
- **API documentation**: https://docs.gptproto.com
- **Other scenes of this model**: `text-to-image`, `image-edit`, `image-to-video` — same auth, different endpoint path and input schema

## Authentication

Every request needs a GPTProto API key in the `Authorization` header. Create one at https://gptproto.com/dashboard/api-key, then export it:

```bash
export GPTPROTO_API_KEY="your-api-key"
```

Header: `Authorization: Bearer $GPTPROTO_API_KEY` (plus `Content-Type: application/json` on POST).

## Pricing

Platform price by tier (USD, already includes the GPTProto discount):

- **832*480 · 5** — $0.225 per run
- **832*480 · 10** — $0.45 per run
- **1280*720 · 5** — $0.45 per run
- **1280*720 · 10** — $0.9 per run
- **1920*1080 · 5** — $0.675 per run
- **1920*1080 · 10** — $1.35 per run

Price range: $0.225 – $1.35 per generation.

Prices may change. The model page always shows the live price: https://gptproto.com/model/qwen/wan-2.5/text-to-video

## API Information

The API is asynchronous: POST the endpoint to create a prediction, then poll its result URL until `status` is `completed` or `failed`.

### Input Schema

The endpoint accepts the following JSON body parameters:

- **`prompt`** (`string`, _required_):
  The positive prompt for the generation.

- **`negative_prompt`** (`string`, _optional_):
  The negative prompt for the generation.

- **`audio`** (`string`, _optional_):
  Audio URL to guide generation (optional). Audio: ≥3s WAV/MP3, ≤15 MB

- **`size`** (`enum`, _optional_):
  The size of the generated media in pixels (width*height).
  - Default: `1280*720`
  - Options: 832*480, 480*832, 1280*720, 720*1280, 1920*1080, 1080*1920

- **`duration`** (`enum`, _optional_):
  The duration of the generated media in seconds.
  - Default: `5`
  - Options: 5, 10

- **`enable_prompt_expansion`** (`boolean`, _optional_):
  If set to true, the prompt optimizer will be enabled.
  - Options: true, false

- **`seed`** (`range`, _optional_):
  The random seed to use for the generation. -1 means a random seed will be used.
  - Default: `-1`
  - Range: -1–2147483647

**Required Parameters Example**:

```json
{
  "prompt": "A tiny origami fox sailing a teacup across a moonlit puddle"
}
```

**Full Example**:

```json
{
  "prompt": "A tiny origami fox sailing a teacup across a moonlit puddle",
  "negative_prompt": "",
  "audio": "",
  "size": "1280*720",
  "duration": 5,
  "enable_prompt_expansion": false,
  "seed": -1
}
```

### Output Schema

Both submit and poll return the same envelope:

- **`data.id`** (`string`): Prediction id. Use it as `result_id` when polling for the result.
- **`data.status`** (`string`): One of `created`, `running`, `completed`, `failed`. See Status Values below.
- **`data.outputs`** (`array of string`): Generated files. Empty until `status` is `completed`; then it holds the output URLs (or base64 strings when the model exposes a base64 option).
- **`data.urls.get`** (`string`): Authoritative result URL for this prediction. Prefer it over building the poll URL yourself.
- **`data.error`** (`string | null`): Failure reason when `status` is `failed`, otherwise `null`.
- **`data.executionTime`** (`integer`): Total processing time in milliseconds.
- **`data.timings.inference`** (`integer`): Model inference time in milliseconds.
- **`data.hasNsfwContents`** (`array of boolean`): Per-output moderation flags.
- **`message`** (`string`): `success` on a normal response, otherwise the error message.
- **`code`** (`integer`): Business status code. `200` means the request was accepted.

**Example Response — submit (task accepted)**:

```json
{
  "data": {
    "id": "pred_example_01",
    "model": "wan-2.5",
    "outputs": [],
    "urls": {
      "get": "https://gptproto.com/api/v3/predictions/pred_example_01/result"
    },
    "hasNsfwContents": [],
    "status": "created",
    "createdAt": "2026-01-01T12:00:00Z",
    "executionTime": 0,
    "timings": {
      "inference": 0
    }
  },
  "message": "success",
  "code": 200
}
```

**Example Response — poll (completed)**:

```json
{
  "data": {
    "id": "pred_example_01",
    "model": "wan-2.5",
    "outputs": [
      "https://oss-us.gptproto.com/example/output.mp4"
    ],
    "urls": {
      "get": "https://gptproto.com/api/v3/predictions/pred_example_01/result"
    },
    "status": "completed",
    "error": null,
    "executionTime": 12345,
    "timings": {
      "inference": 12000
    },
    "has_nsfw_contents": [],
    "created_at": "2026-01-01T12:00:00Z"
  },
  "message": "success",
  "code": 200
}
```

### Status Values

- `created` — Task accepted. Use `data.id` as `result_id` for polling.
- `running` — Generation is in progress. Keep polling.
- `completed` — Finished successfully. Generated files are in `data.outputs`.
- `failed` — Generation failed. Read `data.error` for the reason.

## Usage Examples

### 1. Submit a request

```bash
curl --request POST "https://gptproto.com/api/v3/alibaba/wan-2.5/text-to-video" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "prompt": "A tiny origami fox sailing a teacup across a moonlit puddle",
    "negative_prompt": "",
    "audio": "",
    "size": "1280*720",
    "duration": 5,
    "enable_prompt_expansion": false,
    "seed": -1
  }'
```

```python
import os
import requests

url = "https://gptproto.com/api/v3/alibaba/wan-2.5/text-to-video"
headers = {
  "Authorization": f"Bearer {os.environ['GPTPROTO_API_KEY']}",
  "Content-Type": "application/json"
}
payload = {
  "prompt": "A tiny origami fox sailing a teacup across a moonlit puddle",
  "negative_prompt": "",
  "audio": "",
  "size": "1280*720",
  "duration": 5,
  "enable_prompt_expansion": False,
  "seed": -1
}

response = requests.request("POST", url, headers=headers, json=payload)
print(response.json())
```

```typescript
const response = await fetch("https://gptproto.com/api/v3/alibaba/wan-2.5/text-to-video", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.GPTPROTO_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    prompt: "A tiny origami fox sailing a teacup across a moonlit puddle",
    negative_prompt: "",
    audio: "",
    size: "1280*720",
    duration: 5,
    enable_prompt_expansion: false,
    seed: -1,
  }),
});

const data = await response.json();
console.log(data);
```

### 2. Poll until the task finishes

Replace `YOUR_RESULT_ID` with `data.id` from the submit response (or call `data.urls.get` directly), and keep polling every 1–3 seconds while `status` is `created` or `running`.

```bash
result_id="YOUR_RESULT_ID"

curl --request GET "https://gptproto.com/api/v3/predictions/$result_id/result" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY"
```

```python
import os
import requests

result_id = "YOUR_RESULT_ID"
url = f"https://gptproto.com/api/v3/predictions/{result_id}/result"
headers = {
  "Authorization": f"Bearer {os.environ['GPTPROTO_API_KEY']}"
}
response = requests.request("GET", url, headers=headers)
print(response.json())
```

```typescript
const result_id = "YOUR_RESULT_ID";
const response = await fetch(`https://gptproto.com/api/v3/predictions/${result_id}/result`, {
  method: "GET",
  headers: {
    "Authorization": `Bearer ${process.env.GPTPROTO_API_KEY}`,
  },
});

const data = await response.json();
console.log(data);
```

## Example Prompts

- Studio Ghibli anime style, a bustling ancient Chinese market, streets are crowded with people, vendors are shouting their wares, and children are chasing each other playfully. The background features traditional architecture and waving banners. The camera moves through the crowd…
- A handsome, muscular man with well-defined abs is catching his breath after an intense workout. Sweat drips down his torso. He is shirtless, wearing only black athletic shorts, and is leaning against gym equipment. The lighting comes from the upper side, highlighting the contours…
- A middle-aged man sitting at a wooden desk in a cozy study room, surrounded by bookshelves and a warm lamp glow. He opens an old book and reads aloud with a calm, deep voice: 'History teaches us more than just facts… it shows us who we are.' The room has subtle background sounds:…

## HTTP Status Codes

- `400` — malformed body, a parameter or value this model does not accept, or input blocked by the provider's content moderation
- `401` — missing or invalid API key
- `403` — insufficient credits
- `413` — request body too large
- `429` — rate limited; retry with backoff
- `500` — An internal server error occurred
- `502` — An internal server error occurred
- `504` — Gateway timeout — upstream service did not respond in time; retry later

## Additional Resources

- [Model playground](https://gptproto.com/model/qwen/wan-2.5/text-to-video)
- [API documentation](https://docs.gptproto.com)
- [All models](https://gptproto.com/model)
- [API keys](https://gptproto.com/dashboard/api-key)
- [Platform overview for LLMs](https://gptproto.com/llm-full.txt)
- Any other model: `https://gptproto.com/model/{vendor}/{model}/{scene}/llms.txt`