Documentation
Everything you need to integrate CloudAPI into your application
Welcome to CloudAPI
CloudAPI is a unified API gateway that gives you access to 100+ AI models from OpenAI, Anthropic, Google, Meta, and others through a single endpoint. Built specifically for developers in Central Asia with local payment methods and UZS billing.
Why CloudAPI?
OpenAI-compatible
Drop-in replacement for OpenAI SDK. Just change the base URL.
Local payments
Pay in UZS via Payme, Click, or bank transfer.
100+ models
Access GPT, Claude, Gemini, Llama and many more.
Transparent pricing
Pay only for what you use. No hidden fees.
Next steps
Quickstart
Get up and running in 3 minutes
1. Get your API key
Sign in to your dashboard and create a new API key.
2. Install the SDK
Use the official OpenAI SDK with our base URL.
# Python pip install openai # Node.js npm install openai
3. Make your first request
Send a chat completion request to any model.
from openai import OpenAI client = OpenAI( api_key="cap-...", base_url="https://api.cloudapi.uz/v1" ) response = client.chat.completions.create( model="anthropic/claude-3.5-sonnet", messages=[{"role": "user", "content": "Salom!"}] ) print(response.choices[0].message.content)
Authentication
All API requests require authentication using your API key in the Authorization header.
Header format
Authorization: Bearer cap-abc123xyz...
Never expose API keys in client-side code. Store them as environment variables on your server.
Chat Completions
Generate text responses from any supported model.
Endpoint
POST https://api.cloudapi.uz/v1/chat/completions
Parameters
| Nomi | Type | Tavsif |
|---|---|---|
model | string | Model ID to use (e.g., openai/gpt-4o) |
messages | array | Array of message objects |
temperature | number | Sampling temperature (0-2) |
max_tokens | integer | Maximum tokens to generate |
stream | boolean | Stream response chunks |
Example request
curl https://api.cloudapi.uz/v1/chat/completions \ -H "Authorization: Bearer cap-..." \ -H "Content-Type: application/json" \ -d '{ "model": "anthropic/claude-3.5-sonnet", "messages": [{"role": "user", "content": "Salom!"}], "temperature": 0.7, "max_tokens": 1000 }'
Pricing & Billing
CloudAPI uses pay-as-you-go pricing. You only pay for the tokens you use.
How billing works
- Each model has input and output prices per million tokens
- We add a 30% margin on top of the underlying provider price
- Costs are deducted from your wallet balance in real-time
- View detailed usage and costs in your dashboard
Some models are available for free. Look for the "Free" badge.
Rate Limits
API requests are rate limited per API key to ensure fair usage.
Rate limit headers
X-RateLimit-Limit | Total requests allowed |
X-RateLimit-Remaining | Remaining requests |
X-RateLimit-Reset | Time until reset (seconds) |
Error Handling
CloudAPI returns standard HTTP status codes and OpenAI-compatible error responses.
Common error codes
| Code | Tavsif |
|---|---|
400 | Bad request β invalid parameters |
401 | Unauthorized β invalid API key |
402 | Payment required β insufficient balance |
429 | Too many requests β rate limit exceeded |
500 | Internal server error |
Frequently Asked Questions
How do I get started?
What payment methods do you accept?
Do I need an international card?
Can I use free models?
How is pricing calculated?
Is my data secure?
Can I cancel anytime?
Do you offer support?
Contact us
Need help? Get in touch with our team.
We typically respond within 24 hours