Scope of Model Support
To ensure the stability and maintainability of the AI Central platform in a multi-cloud, multi-model environment, we have established unified support standards for integrated Large Language Models (LLM), Embedding models, speech models, and document recognition models.
This standard is intended to:
-
Reduce the complexity of multi-model compatibility and operations
-
Improve overall performance and controllability
-
Ensure the stable availability of new features on mainstream models
Model Support Levels
Standard Support
-
Definition: Comprehensively included in the product support scope.
-
Requirements: The functionality, performance, and stability have all undergone complete testing, and an SLA (Service Level Agreement) is provided for guarantee.
Experimental Support
-
Definition: The model has been integrated into the main process to ensure that the functionality is available.
-
Requirements: Only basic functionality tests are conducted (interface connectivity, main process can be run through), without performance/stability verification.
-
Marking: Explicitly marked as "experimental" in the product documentation.
Model Categories and Support Status
Large Language Model (LLM)
|
Interface/Vendor |
Supported Model |
Current Support Level |
Notes |
|---|---|---|---|
|
Azure OpenAI |
GPT-5.4, GPT-5.5 |
Standard Support |
|
|
OpenAI |
GPT-5.4, Qwen3.6-Max-Preview, Qwen3.6-Plus, Qwen3.6-Flash, DeepSeek V3.2 |
Standard Support |
|
|
Anthropic |
Claude Sonnet 4.6, Claude Opus 4.6 |
Standard Support |
|
|
Google Vertex |
Gemini 3.1 Pro, Gemini 3.1 Flash |
Standard Support |
|
|
AWS Bedrock |
Claude Sonnet 4.6, Claude Opus 4.6, Llama 4 |
Standard Support |
|
Text-to-Image Models
|
Vendor |
Supported Models |
Current Support Level |
Notes |
|---|---|---|---|
|
Azure |
GPT-Image-1.5, GPT-Image-2 |
Standard Support |
|
|
Alibaba Cloud |
Qwen Image 2.0 |
Standard Support |
|
|
AWS |
Titan Image v2 |
Standard Support |
|
Embedding Models
|
Vendor |
Supported Models |
Current Support Level |
Notes |
|---|---|---|---|
|
Azure |
text-embedding-3-large |
Standard Support |
|
|
Alibaba Cloud |
text-embedding-v4 |
Standard Support |
|
|
AWS |
Amazon Nova Embed |
Standard Support |
|
Image Recognition / OCR
|
Vendor |
Supported Models |
Current Support Level |
Notes |
|---|---|---|---|
|
Azure |
Azure AI Document Intelligence |
Standard Support |
|
|
AWS |
Amazon Textract |
Standard Support |
|
|
Alibaba Cloud |
Alibaba Cloud OCR |
Standard Support |
|
|
Third-party |
TextIn |
Standard Support |
|
Speech Recognition (STT)
|
Vendor |
Supported Models |
Current Support Level |
Notes |
|---|---|---|---|
|
Azure |
Whisper |
Standard Support |
|
Data Source
|
Type |
Examples |
Current Support Level |
Notes |
|---|---|---|---|
|
RDB/DW |
Knowledge Base, Sharepoint |
Standard Support |
|
|
MySQL |
|
Standard Support |
|
|
SQLServer |
|
Standard Support |
|
|
Azure Databricks |
|
Standard Support |
|
|
Snowflake |
|
Standard Support |
|
|
Azure Fabric |
|
Standard Support |
|
Search Engine
|
Type |
Examples |
Current Support Level |
Notes |
|---|---|---|---|
|
Standard Support |
G-bing Search, Meta Search, Tencent Search |
Standard Support |
|
Integration and Validation Requirements
-
Unified API Standards
-
All models must be invoked through the unified Model Gateway service.
-
Request and response formats must comply with the AI Central model API specifications.
-
-
Security and Compliance
-
Calling third-party public APIs without security validation is prohibited.
-
Integrated models must comply with company data compliance requirements (privacy, security, regional restrictions, etc.).
-
-
Performance and Observability
-
Models must support invocation logging and performance monitoring.
-
Health checks and circuit breaker mechanisms must be established for standard support models.
-