AlibabaQwen Embedding
Qwen3.7 Text Embedding
The standard and Flash embedding variants accept up to 131,072 tokens.
Practical use
Practical guidance. Compare shorter passages with whole-document embeddings. A long input limit is useful for some tasks, but one vector may hide a small passage that contains the answer. Choose the document unit before fixing the index.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | qwen3.7-text-embeddingqwen3.7-text-embedding-flash |
| Dimensions | Standard: 256–2560. Flash: 256–1024.Embedding and reranking model catalogue |
Related models
- Qwen3-Embedding-8B
Alibaba · Qwen Embedding
Eight-billion-parameter multilingual embedding model with task instructions and a 32,000-token context.
Launch date not confirmedDownloadable - Qwen3-Embedding-4B
Alibaba · Qwen Embedding
Four-billion-parameter text embedding model for instruction-aware retrieval across more than 100 languages.
Launch date not confirmedDownloadable - Qwen3-Embedding-0.6B
Alibaba · Qwen Embedding
A 600-million-parameter text embedding model with task instructions, over 100 languages and a 32,000-token context.
Launch date not confirmedDownloadable