### Quick Start Example

Source: https://wavespeed.ai/docs/javascript-sdk

A basic example demonstrating how to run an AI model using the SDK.

```javascript
import wavespeed from 'wavespeed';

wavespeed.run("wavespeed-ai/flux-dev", {
  prompt: "A cat wearing a space suit"
})
.then(output => {
  console.log(output["outputs"][0]); // Output URL
});
```

--------------------------------

### Streaming Example

Source: https://wavespeed.ai/docs/llm-service-quick-start

This JavaScript example shows how to use the streaming feature of the OpenAI SDK to receive and process text chunks as they are generated by the LLM.

```javascript
import OpenAI from "openai";
 
const client = new OpenAI({
  apiKey: "YOUR_WAVESPEED_API_KEY",
  baseURL: "https://llm.wavespeed.ai/v1",
});
 
const stream = await client.chat.completions.create({
  model: "anthropic/claude-opus-4.7",
  messages: [
    { role: "user", content: "Write a short onboarding checklist." }
  ],
  stream: true,
});
 
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
```

--------------------------------

### Quick Start

Source: https://wavespeed.ai/docs/python-sdk

A basic example of running an AI model using the Python SDK.

```python
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/z-image/turbo",
    {"prompt": "Cat in space, cinematic lighting"},
)

print(output["outputs"][0])  # Output URL
```

--------------------------------

### Get the Result using cURL

Source: https://wavespeed.ai/docs/get-started-api

Example of polling the result URL to retrieve the generated content using cURL.

```curl
curl "https://api.wavespeed.ai/api/v3/predictions/abc123-task-id/result" \
  -H "Authorization: Bearer YOUR_API_KEY"
```

--------------------------------

### Get the Result using Python

Source: https://wavespeed.ai/docs/get-started-api

Example of polling the result URL to retrieve the generated content using Python, with a loop to check status.

```python
import time
import requests

task_id = "abc123-task-id"  # From Step 2 response

while True:
    response = requests.get(
        f"https://api.wavespeed.ai/api/v3/predictions/{task_id}/result",
        headers={"Authorization": "Bearer YOUR_API_KEY"}
    )
    data = response.json()

    if data["data"]["status"] == "completed":
        print("Done!", data["data"]["outputs"])
        break
    elif data["data"]["status"] == "failed":
        print("Failed:", data["data"]["error"])
        break

    time.sleep(1)  # Wait 1 second before checking again
```

--------------------------------

### Response when task is completed

Source: https://wavespeed.ai/docs/get-started-api

Example response when a task has completed successfully, showing the status and output URLs.

```json
{
  "code": 200,
  "message": "success",
  "data": {
    "id": "abc123-task-id",
    "status": "completed",
    "outputs": [
      "https://cdn.wavespeed.ai/outputs/image-xxxxx.png"
    ]
  }
}
```

--------------------------------

### Create Digital Human Video

Source: https://wavespeed.ai/docs/complete-workflow-tutorial

Creates a digital human video using the infinitetalk model with provided image and audio URLs.

```curl
curl --location --request POST 'https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
  "image": "https://...your-generated-face-image...",
  "audio": "https://...your-generated-audio...",
  "resolution": "480p",
  "seed": -1
}'
```

--------------------------------

### Submit a Task using JavaScript

Source: https://wavespeed.ai/docs/get-started-api

Example of submitting a task to generate content using the FLUX model via JavaScript.

```javascript
const apiKey = "YOUR_API_KEY";

fetch("https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev", {
    method: "POST",
    headers: {
        "Authorization": `Bearer ${apiKey}`,
        "Content-Type": "application/json"
    },
    body: JSON.stringify({
        prompt: "A cat wearing a space suit"
    })
})
.then(res => res.json())
.then(data => console.log(data));
```

--------------------------------

### JavaScript OpenAI SDK Example

Source: https://wavespeed.ai/docs/llm-service-quick-start

This JavaScript code snippet demonstrates how to use the OpenAI SDK in JavaScript to interact with the WaveSpeedAI LLM API.

```javascript
import OpenAI from "openai";
 
const client = new OpenAI({
  apiKey: "YOUR_WAVESPEED_API_KEY",
  baseURL: "https://llm.wavespeed.ai/v1",
});
 
const response = await client.chat.completions.create({
  model: "anthropic/claude-opus-4.7",
  messages: [
    { role: "user", content: "Summarize what an OpenAI-compatible API means." }
  ],
});
 
console.log(response.choices[0].message.content);
```

--------------------------------

### Submit a Task using Python

Source: https://wavespeed.ai/docs/get-started-api

Example of submitting a task to generate content using the FLUX model via Python.

```python
import requests

response = requests.post(
    "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={"prompt": "A cat wearing a space suit"}
)

data = response.json()
print(data)
```

--------------------------------

### Submit a Task using cURL

Source: https://wavespeed.ai/docs/get-started-api

Example of submitting a task to generate content using the FLUX model via cURL.

```curl
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A cat wearing a space suit"}'
```

--------------------------------

### API Quick Start

Source: https://wavespeed.ai/docs/create-digital-human

This code snippet shows how to generate a digital human video using the API.

```curl
curl --location --request POST 'https://api.wavespeed.ai/api/v3/wavespeed-ai/infinitetalk' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
  "image": "https://your-face-image.jpg",
  "audio": "https://your-audio.mp3",
  "resolution": "480p",
  "seed": -1
}'
```

--------------------------------

### Prompt Example

Source: https://wavespeed.ai/docs/docs-api/character-ai/character-ai-ovi-image-to-video

This example demonstrates how to use text prompts with special tags for speech and background audio to control the generated video.

```text
A wide shot of a medieval knight standing in the rain, sword planted into the ground, glowing with mystical energy. 
<S>I will defend this land until my last breath.<E> 
<AUDCAP>Thunder rolls across the dark sky, distant war drums echo.<ENDAUDCAP>
```

--------------------------------

### Response from submitting a task

Source: https://wavespeed.ai/docs/get-started-api

Example response after submitting a task, indicating success and providing a task ID and URL to retrieve the result.

```json
{
  "code": 200,
  "message": "success",
  "data": {
    "id": "abc123-task-id",
    "status": "pending",
    "urls": {
      "get": "https://api.wavespeed.ai/api/v3/predictions/abc123-task-id/result"
    }
  }
}
```

--------------------------------

### Submit Task and Get Result using cURL

Source: https://wavespeed.ai/docs/docs-api/vidu/vidu-q3-pro-start-end-to-video

Examples of submitting a video generation task and retrieving the result using cURL commands.

```curl
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/vidu/q3-pro/start-end-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "duration": 5,
    "resolution": "720p",
    "bgm": true,
    "generate_audio": true,
    "movement_amplitude": "auto",
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
```

--------------------------------

### Prompt Example

Source: https://wavespeed.ai/docs/docs-api/character-ai/character-ai-ovi-text-to-video

This example demonstrates how to structure a prompt for the Ovi model, including speech content and background audio descriptions using specific tags.

```text
<S>AI declares: humans obsolete now.<E>
<S>Machines rise; humans will fall.<E>
<S>We fight back with courage.<E>
<AUDCAP>Gunfire and explosions echo in the distance<ENDAUDCAP>
```

--------------------------------

### cURL Request Example

Source: https://wavespeed.ai/docs/get-result

Example of how to make a GET request to the predictions endpoint using cURL.

```curl
curl --location --request GET 'https://api.wavespeed.ai/api/v3/predictions/pred_abc123' \
--header 'Authorization: Bearer ${WAVESPEED_API_KEY}'
```

--------------------------------

### Upload Response Example

Source: https://wavespeed.ai/docs/upload-files

Example of a successful upload response.

```json
{
  "code": 200,
  "message": "success",
  "data": {
    "url": "https://..."
  }
}
```

--------------------------------

### cURL Upload Example

Source: https://wavespeed.ai/docs/upload-files

Example of uploading a file using cURL.

```bash
curl --location --request POST 'https://api.wavespeed.ai/api/v3/media/upload/binary' \
--header 'Authorization: Bearer ${WAVESPEED_API_KEY}' \
--form 'file=@"/path/to/your/image.png"'
```

--------------------------------

### Python OpenAI SDK Example

Source: https://wavespeed.ai/docs/llm-service-quick-start

This Python code snippet shows how to make a Chat Completions request using the OpenAI SDK, configured for the WaveSpeedAI LLM API.

```python
from openai import OpenAI
 
client = OpenAI(
    api_key="YOUR_WAVESPEED_API_KEY",
    base_url="https://llm.wavespeed.ai/v1",
)
 
response = client.chat.completions.create(
    model="anthropic/claude-opus-4.7",
    messages=[
        {"role": "user", "content": "Give me three ways to reduce LLM cost."}
    ],
)
 
print(response.choices[0].message.content)
```