Reranker API
Explore the API. Make a real request. Use the code in your application.
Top N
top_nNumber of ranked documents to return.
Return documents
return_documentsInclude original document text alongside scores.
Return embeddings
return_embeddingsInclude query and document embeddings.
Maximum document length
max_doc_lengthOptional per-document token limit.
curl 'https://chatsax.com/v1/rerank' \
-X 'POST' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer $CHATSAX_API_KEY" \
--data-binary '{
"model": "",
"query": "",
"top_n": 3,
"documents": [
"",
"",
""
],
"return_documents": true
}'Not connectedPut relevance first.
Refine an existing candidate set by comparing it against your query. Keep retrieval broad, then order the results that deserve attention.
Query-aware ranking
Return original indices and relevance scores for your candidate documents.
Text and visual options
Use a text reranker or m0 for supported text-and-image documents.
Control result size
Choose top_n and whether to return document content.
From playground to production.
Use the same request contract in the browser, an HTTP client, or your agent tools. A Chatsax key keeps access and usage separate from the upstream provider account.
Usage & access
Know what your requests use.
Chatsax currently uses invitation-based access. Request limits are assigned to each key; provider usage is recorded when available. No public checkout or standard price plan is offered here.
Your limits
View the current key’s scopes, minute limit, and daily request limit in the dashboard.
Recorded usage
Inspect requests, response status, latency, and available token counts.
Provider costs
Different services count usage differently. A cancelled or long-running request may still consume upstream resources.
Frequently asked questions
Does reranking search the web?
No. Supply candidate documents from your own index or a Search request.
Are scores probabilities?
Scores describe relative relevance for a query and candidate set. They are not calibrated confidence probabilities.
How do I map results to my input?
Use each result’s index. The returned order is the ranking order, not the original input order.
Is Chatsax operated by Jina AI?
Chatsax is independently operated. Jina supplies the current underlying APIs; model names and source links identify that provider.