Input
Prepare text, image, or document content for vector search and scoring.
Qwen
Qwen3-VL Rerank scores mixed text, image, and video candidates after retrieval. Nfero positions it as a multimodal search and RAG planning route with current official documentation.
Retrieval planning
Use this route to design search, embedding, and reranking flows before enabling production access in Alibaba Cloud.
Prepare text, image, or document content for vector search and scoring.
Use embeddings to collect candidate context for a user query.
Apply Qwen reranking to prioritize the best source passages.
Nfero may earn commission if you later purchase through a qualifying link, at no extra cost to you.
Model playbook
Rank model pages for a developer searching for the right model route.
Embed model descriptions and cluster them by task, cost, and hosted availability.
Rerank model candidates by reasoning, vision, and compatibility.
Terms apply. Confirm usage terms in the customer's Alibaba agreement before production launch.
This route is ready for discovery, pricing estimates, and input planning while live access is prepared.
curl -X POST https://nfero.com/api/models/qwen3-vl-rerank/run \
-H 'content-type: application/json' \
-d '{"query":"","documents":["Alibaba Cloud","Qwen"],"top_k":3}'await fetch('/api/models/qwen3-vl-rerank/run', {
method: 'POST',
headers: { 'content-type': 'application/json' },
body: JSON.stringify({
"query": "",
"documents": [
"Alibaba Cloud",
"Qwen"
],
"top_k": 3
})
});import requests
requests.post('https://nfero.com/api/models/qwen3-vl-rerank/run', json={
"query": "",
"documents": [
"Alibaba Cloud",
"Qwen"
],
"top_k": 3
})