Alibaba Cloud - API - verified
Qwen3.7 Text Embedding embeddings
Qwen3.7 Text Embedding is a current embedding model from Alibaba Cloud, called by API as qwen3.7-text-embedding. It returns 1,024-dimension vectors by default and accepts up to 128,000 input tokens, for text and code input. The first-party list price is $0.07 per 1M input tokens.
CurrentModel id: qwen3.7-text-embedding
- Default dims
- 1,024
- Max input
- 128,000 tok
- Price / 1M
- $0.07
- Inputs
- Text, Code
Dimensions
Flexible output size- 2,560
- 2,048
- 1,536
- 1,024default
- 768
- 512
- 256
Default output: 1,024 dimensions.
Listed sizes: 2,560, 2,048, 1,536, 1,024, 768, 512 and 256.
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
- $0.07
- Batch, per 1M
- Not stated
Singapore price from the embedding docs and synchronous API reference; the model is not yet listed on the Model Studio pricing page and batch discount is not stated per model.
Source: alibabacloud.com/help/en/model-studio/text-embedding-synchronous-api
Usage
Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.
import os
from openai import OpenAI
input_text = "The quality of the clothes is excellent"
client = OpenAI(
# 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"), # If you have not set an environment variable, replace this with your API key.
# This is the URL for the Singapore region. Replace {WorkspaceId} with your workspace ID.
base_url="https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
)
completion = client.embeddings.create(
model="qwen3.7-text-embedding",
input=input_text
)
print(completion.model_dump_json())Worth knowing
Supports 201 languages and dialects, task instructions with text_type query, and dense plus sparse vector output, with up to 20 texts of 128,000 tokens each per request.
Release date not stated in the sources. Multilingual: yes.
FAQ
How many dimensions does Qwen3.7 Text Embedding output?
Default output: 1,024 dimensions. Listed sizes: 2,560, 2,048, 1,536, 1,024, 768, 512 and 256. 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 Qwen3.7 Text Embedding?
128,000 tokens per input, per Alibaba Cloud's documentation. Longer text has to be chunked before you embed it.
How much does Qwen3.7 Text Embedding cost?
The first-party list price is $0.07 per 1M input tokens. Singapore price from the embedding docs and synchronous API reference; the model is not yet listed on the Model Studio pricing page and batch discount is not stated per model. Source: https://www.alibabacloud.com/help/en/model-studio/text-embedding-synchronous-api.
What can Qwen3.7 Text Embedding embed?
Text and code input, per the provider. It is documented as multilingual.
Sources
Last verified from the pages below.
- Model Studio embedding docs - alibabacloud.com
- Text embedding synchronous API - alibabacloud.com
More Alibaba Cloud embedding models
Default dimensions, max input tokens and list price per 1M tokens.
- Qwen3.7 Text Embedding Flashdims not stated - 128,000 tokens - Not stated
- Text Embedding V41,024 dims - 8,192 tokens - $0.07
- Text Embedding V31,024 dims - 8,192 tokens - $0.07
- Tongyi Embedding Vision Plus1,152 dims - 1,024 tokens - $0.09
- Tongyi Embedding Vision Flash768 dims - 1,024 tokens - $0.09
- Qwen3-VL Embedding2,560 dims - 32,000 tokens - $0.10
- Multimodal Embedding V11,024 dims - 512 tokens - Not stated
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.