Qwen3 VL Embedding

Embedding Alibaba Qwen Verified Released Jan 21, 2026

Qwen3-VL-Embedding uses Qwen3-VL to create embeddings for cross-modal retrieval, image and video search, clustering, and tagging. Unlike qwen2.5-vl-embedding, which combines inputs into a shared representation, it also lets each input have its own vector. Summary written by AI Index from Alibaba Qwen’s own pages.

  • In Input modalities: TextImageVideo

Prices

2 offerings · prices as listed
Alibaba Cloud Model Studio (opens in a new tab) Official China · USD qwen3-vl-embedding
Conditions/ 1M tokensInput
Text tokens Standard $0.10
Image tokens $0.258
Video tokens $0.258

Prices from Multimodal embedding API (opens in a new tab) (checked Nov 20, 2026)

Alibaba Cloud Model Studio (opens in a new tab) Official China · CNY qwen3-vl-embedding
ConditionsInput/ 1K tokensInput/ 1M tokens
Text tokens Standard ¥0.0007¥0.70
Image tokens ¥0.0018¥1.80
Video tokens ¥0.0018¥1.80

Prices from 阿里云百炼:模型价格 (opens in a new tab) (checked Nov 9, 2026) · 向量化-大模型服务平台百炼(Model Studio)-阿里云帮助中心 (opens in a new tab) (checked Nov 8, 2026)

Standard: the price a request with no conditions pays (the headline price elsewhere on the site).

Details

Shortest vector
256
Inputs per request
20
Languages
33
Model ID

Not stated on Alibaba Qwen’s pages: vector types.

Cited scores

From third-party leaderboards, not measured by us

No cited leaderboard covers embedding models yet. MTEB’s results are open (CC0); we will cite them per benchmark, never as a combined score.

  1. Now priced on Alibaba Cloud Model Studio, China Input (Image tokens) $0.258 · Input (Video tokens) $0.258 · Input (Text tokens) $0.10
  2. 3 new prices on Alibaba Cloud Model Studio, China Input (Image tokens) ¥0.0018 · Input (Video tokens) ¥0.0018 · Input (Text tokens) ¥0.0007

Sources

Alibaba Qwen’s official policies: data use, privacy, terms →

Alibaba Qwen · China · qwen.ai

Snapshots, the same family and other models from this provider