AI Open Cloud API Documentation
OpenAI-compatible API for text, image, video, audio, 3D, and more. One key, all AI capabilities.
Enter your API key here to test endpoints directly. Get one from your dashboard.
Pricing Overview
8 tiersText Gen
Text Gen
Image Gen
Video Gen
PPT Gen
TTS Soon
Music Soon
3D Gen Soon
Authentication & Models
1 endpointList all available models. Public — no API key required. Prices shown are exactly what you are billed.
{
"object": "list",
"data": [
{
"id": "qwen/qwen-plus",
"name": "Qwen Plus",
"category": "chat",
"aliases": ["text-fast", "text-plus", "gpt-3.5-turbo"],
"context_length": 131072,
"pricing": { "unit": "per_1M_tokens", "input": 1.5, "output": 2 }
}
]
}
Chat
1 endpointChat with AI. Supports streaming (set stream: true).
Authorization: Bearer sk-xxxx
Content-Type: application/json
{
"model": "text-fast",
"messages": [
{ "role": "user", "content": "Hello!" }
],
"stream": false,
"max_tokens": 2000
}
Images
3 endpointsGenerate images from text prompts.
{
"prompt": "A cute cat in space",
"size": "1024x1024",
"model": "image-pro"
}
Edit images based on a reference image and prompt.
{
"image": "https://example.com/image.jpg",
"prompt": "Change style to watercolor",
"model": "image-edit"
}
Analyze and understand images.
{
"imageUrl": "https://example.com/photo.jpg",
"prompt": "Describe this image",
"model": "vision"
}
Video
2 endpointsGenerate videos from text prompts.
{
"prompt": "A cat playing in a garden",
"resolution": "720P",
"duration": 5,
"model": "video"
}
Generate videos from an image.
{
"image": "https://example.com/image.jpg",
"prompt": "Make the character walk",
"duration": 5
}
Audio
2 endpointsText-to-speech synthesis.
{
"text": "Hello world",
"voice": "longxiaochun",
"model": "tts"
}
Generate music from text prompts.
{
"prompt": "Upbeat electronic music for a workout",
"duration": 30
}
3D
1 endpointGenerate 3D models from text or images.
{
"prompt": "A cute robot character",
"image": "https://example.com/robot.jpg",
"model": "3d"
}
PPT
1 endpointGenerate PPT outlines from topics.
{
"topic": "AI Industry Trends 2026",
"slides": 8,
"language": "en"
}
Pricing API
1 endpointGet current API pricing for all models. Public — no API key required. Unified unit: per 1M tokens for chat, per image/video/request for generative media.
{
"success": true,
"currency": "USD",
"pricing": [
{ "model": "qwen/qwen-plus", "unit": "per_1M_tokens", "input": 1.5, "output": 2 },
{ "model": "wan/wan2.6-t2i", "unit": "per_image", "cost": 0.08 }
]
}
SDK Examples
import requests
headers = {"Authorization": "Bearer sk-your-key"}
resp = requests.post(
"https://your-domain.com/api/v1/chat/completions",
headers=headers,
json={"model": "text-fast", "messages": [{"role": "user", "content": "Hello"}]}
)
print(resp.json())
const axios = require('axios');
const resp = await axios.post(
'https://your-domain.com/api/v1/chat/completions',
{ model: 'text-fast', messages: [{ role: 'user', content: 'Hello' }] },
{ headers: { Authorization: 'Bearer sk-your-key' } }
);
console.log(resp.data);
curl -X POST https://your-domain.com/api/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{"model":"text-fast","messages":[{"role":"user","content":"Hello"}]}'