API Documentation

CloudAI is OpenAI-compatible. If you already use OpenAI, you only need to change the base URL and API key.

Base URL

https://api.cloudai.dev/v1

All requests must include the header: Authorization: Bearer YOUR_API_KEY

Available Models

cloudai-turbo

Fastest model. Best for simple tasks, chatbots, and real-time apps.

8K ctx

$0.0002/1K tokens

cloudai-pro

Most capable model. Best for complex reasoning, code, and analysis.

32K ctx

$0.002/1K tokens

cloudai-embed

Text embeddings for semantic search and RAG applications.

512 dims

$0.00001/1K tokens

Endpoints

POST/v1/completions

Generate text completions

Parameter	Type	Required	Description
prompt	string	required	The prompt to complete
model	string	required	Model to use (cloudai-turbo, cloudai-pro)
max_tokens	number	optional	Max tokens to generate (default: 256)
temperature	number	optional	Sampling temperature 0-2 (default: 1.0)

POST/v1/chat/completions

Chat-style completions with conversation history

Parameter	Type	Required	Description
messages	array	required	Array of {role, content} message objects
model	string	required	Model to use
stream	boolean	optional	Stream tokens as they are generated

POST/v1/embeddings

Generate vector embeddings for text

Parameter	Type	Required	Description
input	string \| string[]	required	Text or array of texts to embed
model	string	optional	Embedding model (default: cloudai-embed)