All Products
Search
Document Center

OpenSearch:Model Management

Last Updated:Jun 02, 2026

OpenSearch LLM AI Chat Edition provides built-in large language models (LLMs) and supports adding external LLMs from Alibaba Cloud Model Studio. You can select and integrate LLMs based on your business needs.

Model List

Go to Model Management->LLM to view all LLMs. The list shows the Model Name, Model Type (Built-in LLM, External LLM, or Custom LLM), and Creation Time. You can run Q&A testing from this page.

Model Name

Model Type

Model Description

qwen3-235b-a22b

Built-in LLM

A next-generation Qwen LLM with breakthroughs in inference, instruction following, agent capabilities, and multilingual support across 100+ languages and dialects.

qwen-vl-max

Built-in LLM

A Qwen ultra-large vision-language model that supports image and video multimodal RAG, optimized for complex tasks.

qwen-vl-plus

Built-in LLM

A Qwen ultra-large vision-language model that supports image and video multimodal RAG, optimized for response speed.

opensearch-qwen

Built-in LLM

A model based on Qwen-14b, fine-tuned using retrieval-augmented training data.

opensearch-qwen-plus

Built-in LLM

Based on Qwen-72b, fine-tuned with retrieval-augmented training data. Provides more stable results for the same questions.

deepseek-r1

Built-in LLM

The DeepSeek-R1 model. It performs better on problems such as mathematical reasoning.

deepseek-r1-distill-qwen-7b

Built-in LLM

The deepseek-r1-distill-qwen-7b model in Alibaba Cloud Model Studio.

deepseek-r1-distill-qwen-14b

Built-in LLM

The deepseek-r1-distill-qwen-14b model in Alibaba Cloud Model Studio.

opensearch-llama2-13b

Built-in LLM

A model based on llama2-13b, fine-tuned using retrieval-augmented training data.

opensearch-llama2-13b-turbo

Built-in LLM

An upgraded model based on llama2-13b, fine-tuned using retrieval-augmented training data.

opensearch-llama2-70b

Built-in LLM

A model based on llama2-70b, fine-tuned using retrieval-augmented training data.

opensearch-llama3-8b

Built-in LLM

A model based on llama3-8b, fine-tuned using retrieval-augmented training data.

qwen-turbo

Built-in LLM

The fastest, lowest-cost Qwen model. Suitable for simple tasks.

qwen-plus

Built-in LLM

A balanced Qwen model with performance between qwen-max and qwen-turbo. Suitable for moderately complex tasks.

qwen-max

Built-in LLM

The highest-performing Qwen model. Suitable for complex, multi-step tasks.

qwen2-72b-instruct

Built-in LLM

A balanced Qwen model with performance between qwen-max and qwen-turbo. Suitable for moderately complex tasks. This is a stable version that will not receive further updates.

Note
  • Built-in LLMs only support Q&A testing.

  • External LLMs support details, Q&A testing, editing, and deletion.

  • Custom LLMs support details, Q&A testing, model training, and deletion. Only Professional Edition instances support custom LLMs.