Ali

Qwen3-VL-Reranker-8B

ali/qwen3-vl-reranker-8b
/v1/rerank

Qwen3-VL-Reranker 是 Qwen3 多模态重排序模型系列的最新专有模型,专为视觉-语言相关性建模与精排决策任务设计。该模型基于 Qwen3 系列高性能视觉语言密集基础模型构建,具备强大的跨模态语义对齐与细粒度理解能力,可对文本、图像及其组合进行高精度相关性打分与排序判断。模型支持长上下文输入,能够处理复杂查询、多候选内容与多轮语义条件,在多模态检索增强生成(RAG)、跨模态搜索、内容推荐与审核等场景中显著提升最终结果质量。继承 Qwen3 系列卓越的多语言与视觉推理能力,Qwen3-VL-Reranker 在跨语言与复杂语义匹配任务中表现稳定可靠,并支持指令感知与任务自适应优化,帮助开发者针对不同业务目标实现更高相关性与转化效率。

Input / output modalities
文本 to 文本
Reference input / output price
Input¥0.7Output¥0per 1M tokens
Context window
256K
Added to catalog
Aug 4, 2026

Providers and pricing

ProviderInput /MOutput /MCached /MContextMax outputDetails
siliconflow¥0.7¥0¥0256K64K

siliconflow

Latency
0s
Throughput
0 tokens/s
Context
256K

Pricing

Input
¥0.7/M tokens
Output
¥0/M tokens
Cached
¥0/M tokens

Additional pricing

Input image price
¥1.8

Specifications

Context
256K
Max output
64K
Supported APIs
/v1/rerank

Qwen3-VL-Reranker-8B 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