Embedding-Vision is a vision-centric multimodal embedding model powered by an LLM, featuring outstanding domain-specific performance and high cost-effectiveness in various domains (e.g., e-commerce, photo galleries, security, autonomous driving). With support for text, image, and video, it is applicable to downstream retrieval tasks, including text-to-image, image-to-image, text-to-video and video-to-video.
Inference Service Provider
The inference service provider for tongyi-embedding-vision-plus is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | — |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | — | Max Output Length | — |
Context Window | — |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
- Singapore
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Image Input | 0.5 | Per 1M tokens |
Text Input | 0.5 | Per 1M tokens |
Rate Limits
- China (Beijing)
- Singapore
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 600 |
TPM (Tokens Per Minute) | 200,000 |
Snapshot Versions
tongyi-embedding-vision-plus-2026-03-06
Tongyi-Embedding-Vision is a vision-centric multimodal representation model based on LLM architecture, supporting text, image, and video modalities. Features excellent all-scenario performance, high cost-effectiveness, and visual-centric design, suitable for downstream tasks like image-to-image search, text-to-image search, text-to-video search, video-to-video search, text-to-text search, and text-to-multi-image search. This lightweight version (tongyi-embedding-vision-flash) offers extremely high cost-effectiveness. The 2026-03-06 version achieves comprehensive upgrades in performance and functionality based on Qwen3 architecture while maintaining optimal cost-effectiveness, including multi-resolution modes, multi-vector dimensions, multilingual capabilities, and fused vectors.
Inference Service Provider
The inference service provider for tongyi-embedding-vision-plus-2026-03-06 is Alibaba Cloud Model Studio.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text Image Video | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Unsupported |
Structured Outputs | Unsupported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Unsupported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | — | Max Output Length | — |
Context Window | — |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
- China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Image Input | 0.5 | Per 1M tokens |
Text Input | 0.5 | Per 1M tokens |
Rate Limits
- China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 1200 |
TPM (Tokens Per Minute) | 9,600,000 |