Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Tongyi Embedding Vision

Tongyi Embedding Vision Flash

Independent multimodal retrieval vectors with 768 dimensions and a lower visual-input tariff than Plus.

availableClosed weightsEmbeddings
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
27 of 34 specification fields collected
Input token limit1K1,024 tokens
Vector dimensions768768 dimensions
Input billingSee ratesAlibaba Model Studio · Singapore
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
1,024 tokensSource for Maximum input tokens (opens in a new tab)

Text item limit only, not a combined multimodal request or context limit.

Maximum output
Not collected
Input modalities
Text, Image, VideoSource for Input modalities (opens in a new tab)
Output modalities
EmbeddingsSource for Output modalities (opens in a new tab)

Native API result type takes precedence over generic model-card modality labels.

Reasoning
Not collected
Streaming
Not collected
Knowledge cutoff
Not collected
Release date
2025-09-23Source for Release date (opens in a new tab)

Earliest reviewed regional release; not inferred from a snapshot suffix.

Parameters
Not collected
Architecture
Not collected
API aliases
tongyi-embedding-vision-flashSource for API aliases (opens in a new tab)

Only this exact selector is assigned. Dated variants are not assumed equivalent.

Data retention
Standard inference prompts/responses may be retained for up to 30 days with legal/security exceptions; stateful records/files remain until deleted. Exact-selector zero-data-retention eligibility has not been established in this review.Source for Data retention (opens in a new tab)

Original International policy reference. The domestic Beijing contract was not verified and is not inferred from this policy.

Embedding dimensions
768 dimensionsSource for Embedding dimensions (opens in a new tab)

Fixed output size. The dimension parameter is unsupported for this rolling selector.

Image input limits
Up to 3 MB per image. Supports up to 8 images.Source for Image input limits (opens in a new tab)
Source video limits
Up to 10 MB per video fileSource for Source video limits (opens in a new tab)
Video input formats
MP4, MPEG, AVI, MOV, MPG, WEBM, FLV, MKVSource for Video input formats (opens in a new tab)
Embedding output modes
Independent dense vectors only; no fused embedding modeSource for Embedding output modes (opens in a new tab)
Request mode
DashScope multimodal embedding API; public URLs or Base64 images, public-URL videoSource for Request mode (opens in a new tab)
Video frame sampling
fps: 0–1; default 1 frame/secondSource for Video frame sampling (opens in a new tab)
Embedding input types
Text, image, video and multi_images sequences. Separate vectors are returned for input items.Source for Embedding input types (opens in a new tab)
Usage metering
Text and visual input tokens have separate rates. Output is not billed.Source for Usage metering (opens in a new tab)
Usage accounting
input_tokens includes text, images and video; input_tokens_details separates visual and text tokens. Returned output_tokens is not an output charge.Source for Usage accounting (opens in a new tab)
Free usage allowance
1 million token This free quota is valid for 90 days from the date of Model Studio activation, model release, or application approval, whichever is later.Source for Free usage allowance (opens in a new tab)

Original International Singapore quota. Regional account eligibility can differ.

Request quotas
600 RPM; 200,000 TPMSource for Request quotas (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Alibaba Model Studio · Singapore

Provider source (opens in a new tab)
API model ID
tongyi-embedding-vision-flash
Access
https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/embeddings/multimodal-embedding/multimodal-embedding. Use the matching regional workspace API key.
Regions
Singapore
Request quotas
600 RPM; 200,000 TPMSource for Request quotas (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
EmbeddingsImage/video input1$0.031M tokens
EmbeddingsText input2$0.091M tokens
EmbeddingsImage/video input3CN¥0.201M tokens
EmbeddingsText input3CN¥0.601M tokens

Rate conditions

  1. Standard Singapore rate, excluding promotions. The embedding overview applies this visual rate to images and videos. Input embeddings are not generated answers; no text-question estimate is inferred.
  2. Standard Singapore rate, excluding promotions. Input embeddings are not generated answers; no text-question estimate is inferred.
  3. Published domestic-documentation CNY tariff, not a currency conversion from USD. Singapore rate depends on the account billing currency. The multimodal API overview repeats lower Beijing prices in its Singapore table; the model-specific card differs and is the tariff recorded here. No generated-answer estimate is inferred.
Pricing source (opens in a new tab)Pricing source (opens in a new tab)

Data & enterprise terms

Standard inference prompts/responses may be retained for up to 30 days with legal/security exceptions; stateful records/files remain until deleted. Exact-selector zero-data-retention eligibility has not been established in this review.

Read the service policy (opens in a new tab)

Alibaba Model Studio · China (Beijing)

Provider source (opens in a new tab)
API model ID
tongyi-embedding-vision-flash
Access
https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/embeddings/multimodal-embedding/multimodal-embedding. Use a Beijing workspace API key.
Regions
China (Beijing)
Request quotas
600 RPM; 200,000 TPMSource for Request quotas (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
EmbeddingsImage/video input1CN¥0.151M tokens
EmbeddingsText input1CN¥0.151M tokens

Rate conditions

  1. Published domestic-documentation CNY tariff, not a currency conversion from USD. Beijing workspace. No generated-answer estimate is inferred.
Pricing source (opens in a new tab)

Data & enterprise terms

Account-specific regional retention and enterprise policy require confirmation.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Classification inference: this exact service release is documented as a native Alibaba model, and no corresponding weight release was found in the reviewed official Qwen and Alibaba-NLP inventories. The API documentation does not explicitly establish private checkpoint lineage. Related public Qwen3, GTE, GME and GVE weights are not assumed to implement this selector.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · Singapore31 Oct 2025Source (opens in a new tab)
Platform release · China (Beijing)23 Sept 2025Source (opens in a new tab)

Sources reviewed