Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Alibaba Cloud - API - verified

Tongyi Embedding Vision Plus embeddings

Tongyi Embedding Vision Plus is a current embedding model from Alibaba Cloud, called by API as tongyi-embedding-vision-plus. It returns 1,152-dimension vectors by default and accepts up to 1,024 input tokens, for text, image and video input. The first-party list price is $0.09 per 1M input tokens.

CurrentModel id: tongyi-embedding-vision-plus

Default dims
1,152
Max input
1,024 tok
Price / 1M
$0.09
Inputs
Text, Image, Video

Dimensions

Flexible output size
  • 1,152default

Default output: 1,152 dimensions.

Alibaba Cloud documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

Pricing

Per 1M input tokens
$0.09
Batch, per 1M
Not stated

Singapore (International) price of $0.09 per 1M tokens for text, image and video, with 1 million free tokens for 90 days.

Source: alibabacloud.com/help/en/model-studio/model-pricing

Usage

Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.

Code
image = "https://dashscope.oss-cn-beijing.aliyuncs.com/images/256_1.png"
input = [{'image': image}]
resp = dashscope.MultiModalEmbedding.call(
    # If you have not set an environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx",
    # API keys are region-specific. To get an API key, see https://www.alibabacloud.com/help/model-studio/get-api-key
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    model="tongyi-embedding-vision-plus",
    input=input
)

print(json.dumps(resp.output, indent=4))

Source: alibabacloud.com/help/en/model-studio/embedding

Worth knowing

Produces independent embeddings per input part for image-text retrieval and text-to-image or text-to-video search, with Chinese and English text, up to 8 images of 3 MB and videos up to 10 MB.

Release date not stated in the sources. Multilingual: not stated.

FAQ

How many dimensions does Tongyi Embedding Vision Plus output?

Default output: 1,152 dimensions. Alibaba Cloud documents shorter output vectors for this model (Matryoshka-style), so you can store smaller embeddings by asking for fewer dimensions instead of re-embedding with another model.

What is the max input length of Tongyi Embedding Vision Plus?

1,024 tokens per input, per Alibaba Cloud's documentation. Longer text has to be chunked before you embed it.

How much does Tongyi Embedding Vision Plus cost?

The first-party list price is $0.09 per 1M input tokens. Singapore (International) price of $0.09 per 1M tokens for text, image and video, with 1 million free tokens for 90 days. Source: https://www.alibabacloud.com/help/en/model-studio/model-pricing.

What can Tongyi Embedding Vision Plus embed?

Text, image and video input, per the provider.

Sources

Last verified from the pages below.

More Alibaba Cloud embedding models

Default dimensions, max input tokens and list price per 1M tokens.

Alibaba Cloud (Qwen) API modelsPrices per 1M tokens, context windows and specs for every Alibaba Cloud (Qwen) model in the API registry.

All embedding models

Newsletter

New models, every week

One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.

Keep exploring

Model API pricing and specs

First-party prices per 1M tokens for chat and reasoning models.

Local models

Open-weight LLMs you can download and run, with sizes and licenses.

What is RAG?

Where embeddings fit in a retrieval pipeline, end to end.

Vector databases compared

Where the vectors go once you have picked a model.