Alibaba Cloud
Qwen Cloud's model-selection docs list text-embedding-v4, tongyi-embedding-vision-plus and qwen3-rerank for search, RAG and retrieval accuracy improvement.
Editorial verdict
Teams building RAG, semantic search or ranking pipelines around Chinese and multilingual content.
Avoid choosing it only from model specs; run corpus-level retrieval checks first.
Qwen Cloud includes retrieval infrastructure models, so Qwen coverage should include more than chat and generation.
Pay-as-you-go retrieval API billing varies by model
Qwen Cloud billing, Pay-as-you-go API billing
Commercial use should follow the current product, API, model license and billing terms.
Review prompt, file, media upload, retention and training-use terms before sensitive workloads.
Use embeddings and rerankers to build retrieval and answer pipelines.
Use multimodal embedding when text and image search need one retrieval layer.
Model names, quotas, release status, regional access and commercial terms can change quickly; recheck official sources before procurement or production use.
qwen
deepseek
zhipu-glm
docs · en · verified 2026-08-04
Lists text-embedding-v4, tongyi-embedding-vision-plus and qwen3-rerank.
Last checked: 2026-08-04