Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Alibaba Cloud / Qwen3.7 Embedding

Qwen3.7 Text Embedding Flash

A lower-cost multilingual text embedding model with four vector sizes and Beijing batch pricing.

Embeddings
availableClosed weightsEmbeddings
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
23 of 29 specification fields collected
Input token limit128K128,000 tokens
Vector dimensions1024, 768, 512, 256See specification notes below
Input billingSee ratesAlibaba Model Studio · China (Beijing)
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
131,072 tokensSource for Context / input limit (opens in a new tab)
Maximum input tokens
128,000 tokensSource for Maximum input tokens (opens in a new tab)

API limit per item. The model card lists 131,072 input/context tokens, so the lower API limit is shown.

Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
EmbeddingsSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Structured output
Not supportedSource for Structured output (opens in a new tab)
Streaming
Not collected
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Knowledge cutoff
Not collected
Release date
2026-09-01Source for Release date (opens in a new tab)

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

Parameters
Not collected
Architecture
Not collected
Languages
Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, RussianSource for Languages (opens in a new tab)

Named examples, not a complete enumeration.

Context caching
Not supportedSource for Context caching (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
API aliases
qwen3.7-text-embedding-flashSource for API aliases (opens in a new tab)

Pinned and rolling selectors are separate records; equivalence is not asserted.

Embedding dimensions
1024, 768, 512, 256Source for Embedding dimensions (opens in a new tab)
Default vector dimensions
1,024Source for Default vector dimensions (opens in a new tab)
Items per embedding request
20Source for Items per embedding request (opens in a new tab)
Embedding output modes
Dense vectors; sparse capability claimed by the card, exact request support needs confirmationSource for Embedding output modes (opens in a new tab)

The API output_type parameter list omits Flash even though the model card advertises sparse capability.

Language coverage
201 major languages and dialectsSource for Language coverage (opens in a new tab)
Request mode
OpenAI-compatible embeddings or DashScope text embedding, BeijingSource for Request mode (opens in a new tab)
Usage accounting
OpenAI-compatible response returns prompt_tokens and total_tokensSource for Usage accounting (opens in a new tab)
Free usage allowance
1 million tokens; 90 days from the latest of activation, model release or application approvalSource for Free usage allowance (opens in a new tab)
Request quotas
24,000 RPM; 1,000,000 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 · China (Beijing)

Provider source (opens in a new tab)
API model ID
qwen3.7-text-embedding-flash
Access
https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/compatible-mode/v1/embeddings. Use a Beijing workspace API key. Text embedding also supports the DashScope text-embedding API.
Regions
China (Beijing)
Tool calling
Not supportedSource for Tool calling (opens in a new tab)
Structured output
Not supportedSource for Structured output (opens in a new tab)
Search grounding
Not supportedSource for Search grounding (opens in a new tab)
Prefix completion
Not supportedSource for Prefix completion (opens in a new tab)
Context caching
Not supportedSource for Context caching (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not supportedSource for Fine-tuning (opens in a new tab)
Request quotas
24,000 RPM; 1,000,000 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
EmbeddingsText input1CN¥0.1251M tokens
Batch embeddingsBatch text input2CN¥0.0631M tokens

Rate conditions

  1. Published domestic-documentation CNY tariff, not a currency conversion from USD. Beijing workspace. No generated-answer estimate is inferred.
  2. API guide publishes CNY 0.000063 per 1,000 input tokens; normalized exactly to 0.063 per million. Separate asynchronous Batch API, not a synchronous array discount.
Pricing source (opens in a new tab)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: the provider names this native API release separately from public Qwen3/GTE/GME/GVE checkpoints, and no exact release was found in the reviewed official Qwen or Alibaba-NLP weight inventories. Absence is supporting evidence, not proof of private checkpoint lineage. Base-model parameter counts are not transferred to this service.

Classification evidence (opens in a new tab)

Lifecycle dates

Platform release · China (Beijing)1 Sept 2026Source (opens in a new tab)

Sources reviewed