Alibaba · embedding
Qwen3 Embedding 8B
Qwen3 Embedding 8B is a downloadable text-embedding checkpoint for semantic retrieval, clustering and code search. It has a documented 32K input window and up to 4,096 vector dimensions.
Downloadable checkpoint · apache-2.0
Official sources reviewed 2026-10-02. This page documents access and specifications; it does not report a model benchmark.
Task and deployment contract
Downloadable checkpoint; run the task-specific inference code linked below.
The official model table lists 8B parameters and 4,096 embedding dimensions. Custom dimensions are supported; record the chosen dimension with every vector index.
The query can include a task instruction. Encode corpus documents with the documented document format; do not mix embeddings from different checkpoints in the same index.
Use the repository examples for Transformers, sentence-transformers or a compatible task-serving runtime. A chat-completions request does not produce embeddings.
These checkpoint specifications differ from the hosted text-embedding-v4 and Qwen3.7 API contracts. No hosted rate for this exact checkpoint is asserted here.
Billing and limits
No current provider rate for this exact configuration is recorded here. Open weights still require compute and operations; an unlisted rate does not mean a hosted API is free.
Recorded input window: 32,768 tokens. Apply the endpoint's stricter request and batch limits when applicable.
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.