Ali

Qwen3-Embedding-0.6B

ali/qwen3-embedding-0.6b
/v1/embeddings

Qwen3-Embedding-0.6B 是 Qwen3 嵌入模型系列的最新专有模型,专为文本嵌入和排序任务设计。该模型基于 Qwen3 系列的密集基础模型,具有 6 亿参数规模,支持长达 32K 的上下文长度,可生成最高 1024 维的嵌入向量。模型继承了基础模型卓越的多语言能力,支持超过 100 种语言,具备长文本理解和推理能力。在 MTEB 多语言排行榜上表现优异(得分 64.33),在文本检索、代码检索、文本分类、文本聚类和双语挖掘等多项任务中表现出色。模型支持用户自定义输出维度(32 到 1024)和指令感知功能,可根据特定任务、语言或场景进行优化,为需要平衡效率和效果的应用场景提供理想选择

Input / output modalities
Not provided to Not provided
Reference input / output price
Input¥0.07Output¥0per 1M tokens
Context window
1M
Added to catalog
Aug 3, 2026

Providers and pricing

ProviderInput /MOutput /MCached /MContextMax outputDetails
siliconflow¥0.07¥0¥01M64K

siliconflow

Latency
0s
Throughput
0 tokens/s
Context
1M

Pricing

Input
¥0.07/M tokens
Output
¥0/M tokens
Cached
¥0/M tokens

Specifications

Context
1M
Max output
64K
Supported APIs
/v1/embeddings

Qwen3-Embedding-0.6B code examples and API guide

The upstream response does not declare a public API protocol that can be represented safely. Unknown protocols are not guessed.

No public applications are currently listed for this model.

Related Models