Tongyi Embedding Vision Flash (2026-03-06)

Embedding Alibaba Qwen Verified Released Mar 20, 2026

tongyi-embedding-vision-flash-2026-03-06 is a multimodal embedding model for search across text, images, and video, positioned as the lightweight option alongside tongyi-embedding-vision-plus. It supports both independent embeddings and fused embeddings that combine inputs for retrieval. Summary written by AI Index from Alibaba Qwen’s own pages.

  • In Input modalities: TextImageVideo

Prices

1 offering · prices as listed
Alibaba Cloud Model Studio (opens in a new tab) Official China · CNY tongyi-embedding-vision-flash-2026-03-06
Conditions/ 1K tokensInput
Standard ¥0.00015

Prices from 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 7, 2026)

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

Details

Shortest vector
64
Inputs per request
20
Languages
30
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. New embedding model

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