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.
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
Application Layer
Business applications & clients
Receives client requests and performs authentication, authorization, and traffic control
API Gateway Layer
Request routing & authorization
Intelligent routing and load balancing, forwarding requests to the appropriate LLM service
Forwarding Service Layer
Core business logic
Request handling, response transformation, error handling
LLM Service Layer
LLM API integration
Integrates multiple LLM APIs (OpenAI, Claude, domestic Chinese LLMs, and more)
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
- • /v1/chat/completions
- • /v1/responses
- • /v1/responses/compact
- • /v1/messages
- • /v1beta/models
- • /v1/embeddings
- • /v1/rerank
- • /v1/images/generations
- • /v1/images/edits
- • /v1/images/variations
- • /v1/audio/speech
- • /v1/audio/transcriptions
- • /v1/audio/translations