AI + Infrastructure

The Unified LLM API Gateway. Better pricing, more stable, no subscription required -- just swap the BASE URL to get started. Supports 30+ LLM providers, delivering secure, stable, and efficient API forwarding and management.

Status: Live

Get Started

Better pricing, more stable, no subscription required -- just swap the BASE URL to get started.

Core Features

A complete LLM API relay service

Unified Access

The Unified LLM API Gateway -- better pricing, more stable, no subscription required

  • Supports 30+ LLM providers
  • Unified interface standard
  • Seamless model switching
  • Ready to use

Chat & Completion

Supports a range of chat and text-completion API endpoints

  • /v1/chat/completions
  • /v1/responses
  • /v1/messages
  • /v1beta/models

Image & Embeddings

Provides image generation, editing, and vector-embedding services

  • /v1/embeddings
  • /v1/rerank
  • /v1/images/generations
  • /v1/images/edits

Voice Services

Supports speech synthesis, transcription, and translation

  • /v1/audio/speech
  • /v1/audio/transcriptions
  • /v1/audio/translations
  • Multi-language support

Use Cases

Infrastructure support for a wide range of AI applications

AI + Motion Control

Provides LLM inference for motion-control algorithms, optimizing trajectory planning

Example Use

Real-time path planning, adaptive parameter tuning

AI + Vision Inspection

Provides inference services for vision models, enabling intelligent defect detection and classification

Example Use

Product quality inspection, anomaly recognition

AI + Data Analysis

Provides intelligent data analysis and prediction services for the Industrial IoT platform

Example Use

Equipment failure prediction, production-optimization recommendations

Service Architecture

A layered design, easy to extend and maintain

1

Application Layer

Business applications & clients

Receives client requests and performs authentication, authorization, and traffic control

2

API Gateway Layer

Request routing & authorization

Intelligent routing and load balancing, forwarding requests to the appropriate LLM service

3

Forwarding Service Layer

Core business logic

Request handling, response transformation, error handling

4

LLM Service Layer

LLM API integration

Integrates multiple LLM APIs (OpenAI, Claude, domestic Chinese LLMs, and more)

5

Monitoring & Logging

Security & audit

Real-time monitoring of API call status, with detailed access logs and usage statistics

Quick Integration

Simple API calls, fast onboarding

# Usage example - Python
import openai

# Configure the API endpoint and key
openai.api_base = "https://model.openindu.com/v1"
openai.api_key = "your-api-key"

# Call the LLM API
response = openai.ChatCompletion.create(
  model="gpt-4",
  messages=[
    { "role": "user", "content": "Analyze this batch of product quality data" }
  ]
)
print(response.choices[0].message.content)

💡 Supported API Endpoints

Chat & Completion
  • • /v1/chat/completions
  • • /v1/responses
  • • /v1/responses/compact
  • • /v1/messages
Embeddings & Reranking
  • • /v1beta/models
  • • /v1/embeddings
  • • /v1/rerank
Image Services
  • • /v1/images/generations
  • • /v1/images/edits
  • • /v1/images/variations
Voice Services
  • • /v1/audio/speech
  • • /v1/audio/transcriptions
  • • /v1/audio/translations