API Documentation

HuosuAI provides a fully OpenAI-compatible RESTful API supporting chat completions, text embeddings, image generation, and more.

Base URL

https://api.huosu.com/v1

All API requests must use HTTPS.

Authentication

HuosuAI uses Bearer Token authentication. Include your API Key in the HTTP header:

Authorization: Bearer YOUR_API_KEY

Supported Endpoints

Chat Completions

POST /v1/chat/completions

The primary conversation endpoint supporting multi-turn dialogue, streaming, function calling, and JSON Mode.

Request Example:

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Explain what a large language model is."}
  ],
  "temperature": 0.7,
  "max_tokens": 2048,
  "stream": false
}

Key Parameters:

Parameter	Type	Required	Description
model	string	Yes	Model identifier, e.g. gpt-4o, claude-sonnet-4-20250514
messages	array	Yes	Array of conversation messages with role and content
temperature	number	No	Sampling temperature, 0-2, default 1
max_tokens	integer	No	Maximum tokens to generate
stream	boolean	No	Enable streaming output, default false
tools	array	No	Function calling tool definitions
response_format	object	No	Response format control, e.g. {"type": "json_object"}

Embeddings

POST /v1/embeddings

Convert text to vector representations for semantic search, similarity computation, and RAG applications.

Image Generations

POST /v1/images/generations

Generate images from text descriptions using models like DALL-E.

Models

GET /v1/models

List all currently available models.

Audio Transcriptions

POST /v1/audio/transcriptions

Convert audio files to text using Whisper models.

Moderations

POST /v1/moderations

Check text content for policy violations.

Error Codes

HTTP Status	Error Type	Description
400	invalid_request_error	Invalid request parameters
401	authentication_error	Invalid or expired API Key
403	permission_error	No permission to access the resource
429	rate_limit_error	Rate limit exceeded, retry later
500	server_error	Internal server error
502	upstream_error	Upstream model service error

Rate Limits

Limit	Default	Description
Requests per minute	60 RPM	Can be increased upon request
Concurrency	10	Simultaneous requests
Max payload	10 MB	Per request body size