Providers and ModelsAlibaba Cloud

Qwen3-Rerank

Qwen3-Rerank
Alibaba Cloud · Reranker
POST /v1/reranks

Semantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.

At a glance

FieldValue
Model idqwen3-rerank
Input modalitiesText
Output modalitiesRanking
Context window4000
Weight precision-
RegionSingapore
Featuressemantic ranking, multilingual, rag, custom instructions
Native inferenceNo
NewYes
Supported endpointsPOST /v1/reranks

Pricing

ChargeSpecRate
Inputper 1M prompt tokens$0.10

Example request

$curl https://api.empiriolabs.ai/v1/reranks \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "qwen3-rerank", "query": "What is a rerank model?", "documents": ["Rerank models sort candidate documents by relevance.", "Quantum computing is a cutting-edge field of computer science.", "Pre-trained language models advanced rerank models."], "top_n": 2, "return_documents": true}'

Parameters

ParameterTypeRequiredDefaultDescription
querystringyes—Query text to rank documents against. Max 4,000 tokens.
documentsarrayyes—Candidate documents to sort (strings). Max 500 items, each up to 4,000 tokens.
top_nnumberno10Number of top-ranked documents to return. Defaults to all. · Range: 1 – 500
instructstringno"Given a web search query, retrieve relevant passages that answer the query."Custom English instruction. Use “Retrieve semantically similar text.” for similarity sorting.
return_documentsbooleannofalseWhen true, return the original document text alongside each result.

Notes

Per-request limits

  • Up to 500 candidate documents per request
  • Max 4,000 tokens per query/document
  • Max 120,000 tokens per request (formula: query_tokens × n_docs + sum_of_doc_tokens)
  • Tokens billed are query+documents combined; only successful reranks are charged

Languages

  • 100+ major languages including Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, Russian

Sorting modes (instruct parameter)

  • Default — Q&A retrieval: Given a web search query, retrieve relevant passages that answer the query.
  • Semantic similarity: Retrieve semantically similar text.
  • Or any custom English instruction (see model task prompts)

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-rerank.