All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 Reranker 4B

Reranking model for improving retrieval quality in search and recommendation systems

Model facts

Context window
33K tokens
Maximum output
8K tokens
Cheapest paid input
$0.058 per 1M tokens
Cheapest paid output
free per 1M tokens
Open weights
yes
Providers
2

Capabilities and modalities

open weights, text.

Observed price history

  • 2026-08-24: $0.058 input / free output per 1M tokens

API providers