Alibaba Cloud: Tongyi Embedding Vision Plus

Tongyi Embedding Vision Plus creates vector representations for visual and textual material. It is useful for mixed-media catalogs, where a search system needs to connect pictures with captions or related content.

Compare models

tongyi-embedding-vision-plus

AvailableAlibaba CloudEmbeddingSync

Input / Output: $0.09 / —
Modalities: EmbeddingVision

About Tongyi Embedding Vision Plus

Tongyi Embedding Vision Plus is an Alibaba multimodal embedding model that produces vectors for text, images, and video. It outputs a single fixed size of 1152 dimensions, supports Chinese and English, and can take a sequence of up to 8 images. Unlike Qwen3-VL-Embedding it returns independent embeddings only, with no fusion mode or adjustable size.

Where it works well

Embeds text, images, and video in one vector space for cross-modal lookup.
Accepts a sequence of up to eight images in one input.
Fixed 1152-dimension output keeps index design simple.
Fits Chinese and English catalogues, the two languages Alibaba lists for it.

When to choose another model

Languages are limited to Chinese and English, whereas Qwen3-VL-Embedding covers 33.
Dimensions cannot be changed, and fused embeddings are not offered.

Getting started

Create API key
Create a key in Console, then use it with every model on the platform.

Send your first request

Copy the example for your language and run it against the endpoint.

Multimodal embeddingTokenLab endpoint

POST/v1/multimodal/embeddings

curl -X POST "https://api.tokenlab.sh/v1/multimodal/embeddings" \
  -H "Authorization: Bearer sk-xxx" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "tongyi-embedding-vision-plus",
  "input": {
    "text": "The quick brown fox jumps over the lazy dog."
  }
}'

Parameters

Multimodal embedding

Parameter	Values and limits	Default	Notes
`dimensions`	Not provided	Not provided	This field is accepted. The current public contract does not specify a complete value range or list. No additional values are promised. The omitted-field default is not verified.
`input`	Not provided	Not provided	Not provided
`input_modality`	Not provided	Not provided	Not provided

TokenLab currently keeps image input behind ENABLE_MULTIMODAL_IMAGE_INPUT; public contract should not promise image/video input until live probes and docs are opened end to end.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Default

per 1M tokens

Official price: Input $0.09 / Text Input $0.09 / Image Input $0.09
Verified price: —
Discount: —

	Official priceper 1M tokens	Verified priceper 1M tokens	Discount
Default	Input $0.09 / Text Input $0.09 / Image Input $0.09	—	—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours

Requests
Success rate
P95 latency
Total tokens

Model performance

Last updated Nov 1, 2026, 8:13 AM UTC

Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open Tongyi Embedding Vision Plus in Console with a prompt ready to edit or send.

Help me try tongyi-embedding-vision-plus with multimodal-embedding at /v1/multimodal/embeddings. Show the result and cost.

Use cases

Best for

Vision

Mixed-media catalogues
Index product photos and descriptions together so that text queries retrieve the matching pictures.
Image sequence matching
Embed a sequence of up to eight images, such as a product shot series, and compare it with text.
Caption pairing
Link pictures to captions or related articles by nearest-vector search across a mixed-media archive.

Prompt examples

Embed this series of six product photos so it can be searched with text.

Embed the Chinese query '白色运动鞋' to retrieve matching shoe images.

Embed this clip and its caption separately and compare their vectors.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

What vector size does Tongyi Embedding Vision Plus return?

1152 dimensions, fixed. Alibaba does not list alternative sizes for this model, so index design can assume one vector width for everything. Check that your vector database is configured for that width.

Which languages does it work with?

Chinese and English, according to Alibaba's reference. Queries in other languages are not covered, so use Qwen3-VL-Embedding when you need wider language coverage for your search.

Can I embed several images at once?

Yes, as a multi-image input of up to 8 images, though each result is an independent embedding rather than a fused one that merges the images.

When should I pick Qwen3-VL-Embedding instead?

When you need adjustable dimensions, fused embeddings, or languages beyond Chinese and English, all of which Qwen3-VL-Embedding provides and this model does not. Pick it also when your queries are in several languages.

How much does Tongyi Embedding Vision Plus cost?

Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should Tongyi Embedding Vision Plus use?

Use https://api.tokenlab.sh/v1/multimodal/embeddings for Tongyi Embedding Vision Plus. The request example below shows the matching code shape.

Which operations does Tongyi Embedding Vision Plus support?

Tongyi Embedding Vision Plus supports Multimodal embedding. Select an operation above to see its endpoint and request example.