All Products
Search
Document Center

OpenSearch:Supported services

Last Updated:Apr 01, 2026

The AI Search Open Platform is compatible with the OpenAI API. You can call its services using the OpenAI SDK.

Two categories of services are available: Text embedding and Content generation.

Text embedding

Use these models to convert text into vector representations for semantic search and similarity tasks.

ModelIDLanguages supportedMax input (tokens)Output dimensions
OpenSearch Text Embedding Service-001ops-text-embedding-00140+3001536
OpenSearch General Text Embedding Service-002 (recommended)ops-text-embedding-002100+81921024
OpenSearch Text Embedding Service-Chinese-001ops-text-embedding-zh-001Chinese only1024768
OpenSearch Text Embedding Service-English-001ops-text-embedding-en-001English only512768

Not sure which to pick? Start with OpenSearch General Text Embedding Service-002 (ops-text-embedding-002). It supports the widest range of languages and accepts the longest input, making it the best general-purpose choice. Use the language-specific models when you need to optimize for a single language.

For API usage details, see Text Embedding.

Content generation

Use these models for retrieval-augmented generation (RAG) and other language tasks.

OpenSearch-tuned model

ModelIDDescription
OpenSearch-Qwen-Turboops-qwen-turboBuilt on qwen-turbo with supervised fine-tuning and retrieval-augmented generation. Optimized for safety and relevance.

Qwen series

ModelIDBest for
Qwen-Turboqwen-turboSimple tasks. Fastest and most cost-effective in the Qwen series.
Qwen-Plusqwen-plusMedium-complexity tasks. Balances inference quality, cost, and speed between Qwen-Max and Qwen-Turbo.
Qwen-Maxqwen-maxComplex, multi-step tasks. Highest-performing model in the Qwen series.

For full model specifications, see the Model List for Qwen-Turbo, Qwen-Plus, and Qwen-Max.

DeepSeek series

ModelIDDescription
DeepSeek-R1deepseek-r1Optimized for complex reasoning tasks. Excels at understanding complex instructions and delivering accurate results.
DeepSeek-V3deepseek-v3Mixture of Experts (MoE) architecture. Strong in long-context understanding, coding, math, encyclopedic knowledge, and Chinese language tasks.
DeepSeek-R1-distill-qwen-7bdeepseek-r1-distill-qwen-7bQwen-7B model fine-tuned on DeepSeek-R1 training samples via knowledge distillation.
DeepSeek-R1-distill-qwen-14bdeepseek-r1-distill-qwen-14bQwen-14B model fine-tuned on DeepSeek-R1 training samples via knowledge distillation.

For API usage details, see Content Generation.