Reranker

Maximize the search relevancy and RAG accuracy with our cutting-edge reranker API.

Reranker API

Try our cutting-edge reranker API to maximize your search relevancy and RAG accuracy. Starting for free!

Auto preview

Raise issue

FAQ

Status

Select reranker

Number of returned documents

The number of most relevant documents to return for the query.

Example query

Change it and see how the response changes!

Example candidate documents to rank

Change them and see how the response changes!

Request

Bash

Language

curl https://api.jina.ai/v1/rerank \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer " \
  -d @- <<EOFEOF
  {
    "query": "Organic skincare products for sensitive skin",
    "top_n": 3,
    "documents": [
        "Organic skincare for sensitive skin with aloe vera and chamomile: Imagine the soothing embrace of nature with our organic skincare range, crafted specifically for sensitive skin. Infused with the calming properties of aloe vera and chamomile, each product provides gentle nourishment and protection. Say goodbye to irritation and hello to a glowing, healthy complexion.",
        "New makeup trends focus on bold colors and innovative techniques: Step into the world of cutting-edge beauty with this seasons makeup trends. Bold, vibrant colors and groundbreaking techniques are redefining the art of makeup. From neon eyeliners to holographic highlighters, unleash your creativity and make a statement with every look.",
        "Bio-Hautpflege für empfindliche Haut mit Aloe Vera und Kamille: Erleben Sie die wohltuende Wirkung unserer Bio-Hautpflege, speziell für empfindliche Haut entwickelt. Mit den beruhigenden Eigenschaften von Aloe Vera und Kamille pflegen und schützen unsere Produkte Ihre Haut auf natürliche Weise. Verabschieden Sie sich von Hautirritationen und genießen Sie einen strahlenden Teint.",
        "Neue Make-up-Trends setzen auf kräftige Farben und innovative Techniken: Tauchen Sie ein in die Welt der modernen Schönheit mit den neuesten Make-up-Trends. Kräftige, lebendige Farben und innovative Techniken setzen neue Maßstäbe. Von auffälligen Eyelinern bis hin zu holografischen Highlightern – lassen Sie Ihrer Kreativität freien Lauf und setzen Sie jedes Mal ein Statement.",
        "Cuidado de la piel orgánico para piel sensible con aloe vera y manzanilla: Descubre el poder de la naturaleza con nuestra línea de cuidado de la piel orgánico, diseñada especialmente para pieles sensibles. Enriquecidos con aloe vera y manzanilla, estos productos ofrecen una hidratación y protección suave. Despídete de las irritaciones y saluda a una piel radiante y saludable.",
        "Las nuevas tendencias de maquillaje se centran en colores vivos y técnicas innovadoras: Entra en el fascinante mundo del maquillaje con las tendencias más actuales. Colores vivos y técnicas innovadoras están revolucionando el arte del maquillaje. Desde delineadores neón hasta iluminadores holográficos, desata tu creatividad y destaca en cada look.",
        "针对敏感肌专门设计的天然有机护肤产品：体验由芦荟和洋甘菊提取物带来的自然呵护。我们的护肤产品特别为敏感肌设计，温和滋润，保护您的肌肤不受刺激。让您的肌肤告别不适，迎来健康光彩。",
        "新的化妆趋势注重鲜艳的颜色和创新的技巧：进入化妆艺术的新纪元，本季的化妆趋势以大胆的颜色和创新的技巧为主。无论是霓虹眼线还是全息高光，每一款妆容都能让您脱颖而出，展现独特魅力。",
        "敏感肌のために特別に設計された天然有機スキンケア製品: アロエベラとカモミールのやさしい力で、自然の抱擁を感じてください。敏感肌用に特別に設計された私たちのスキンケア製品は、肌に優しく栄養を与え、保護します。肌トラブルにさようなら、輝く健康な肌にこんにちは。",
        "新しいメイクのトレンドは鮮やかな色と革新的な技術に焦点を当てています: 今シーズンのメイクアップトレンドは、大胆な色彩と革新的な技術に注目しています。ネオンアイライナーからホログラフィックハイライターまで、クリエイティビティを解き放ち、毎回ユニークなルックを演出しましょう。"
    ]
  }
EOFEOF

API key

Available tokens

This is your unique key. Store it securely!

The goal of a search system is to find the most relevant results quickly and efficiently. Traditionally, methods like BM25 or tf-idf have been used to rank search results based on keyword matching. Recent methods, such as embedding-based cosine similarity, have been implemented in many vector databases. These methods are straightforward but can sometimes miss the subtleties of language, and most importantly, the interaction between documents and a query's intent. This is where the "reranker" shines. A reranker is an advanced AI model that takes the initial set of results from a search—often provided by an embeddings/token-based search—and reevaluates them to ensure they align more closely with the user's intent. It looks beyond the surface-level matching of terms to consider the deeper interaction between the search query and the content of the documents.

Here's how it works:

Initial Retrieval

A search system uses embeddings/BM25 to find a broad set of potentially relevant documents based on the user's query.

Reranking

The reranker then takes these results and analyzes them at a more granular level, considering the nuances of how the query terms interact with the document content.

Improved Results

It reorders the search results, placing the ones it deems most relevant at the top, based on this deeper analysis.

The reranker can significantly improve the search quality because it operates at a sub-document and sub-query level, meaning it looks at the individual words and phrases, their meanings, and how they relate to each other within the query and the documents. This results in a more precise and contextually relevant set of search results.

Jina Reranker v2 is the best-in-class reranker released on Jun 25th 2024; it is built for Agentic RAG. It features function-calling support, multilingual retrieval for over 100 languages, code search capabilities, and offers a 6x speedup over v1. Read more about v2 model.

Multilingual Retrieval

Reranker v2 enables document retrieval in over 100 languages, regardless of the query language.

Function-Calling & Code Search

Reranker v2 ranks code snippets and function signatures based on natural language queries, ideal for Agentic RAG applications.

Tabular and Structured Data Support

Reranker v2 ranks the most relevant tables based on natural language queries, helping to sort different table schemas and identify the most relevant one before generating an SQL query.

Three Ways to Purchase

Subscribe to our API, purchase through cloud providers, or obtain a commercial license for your organization.

With 3 cloud service providers

Using AWS or Azure? You can deploy our models directly on your company's cloud platform and handle billing through the CSP account.

With Jina Search Foundation API

The easiest way to access all of our products. Top-up tokens as you go.

Enter the API key you wish to recharge

Top up this API key with more tokens

Depending on your location, you may be charged in USD, EUR, or other currencies. Taxes may apply.

Please input the right API key to top up

Understand the rate limit

Rate limits are the maximum number of requests that can be made to an API within a minute per IP address (RPM). Find out more about the rate limits for each product and tier below.

Rate Limit

Rate limits are tracked in two ways: RPM (requests per minute) and TPM (tokens per minute). Limits are enforced per IP and can be reached based on whichever threshold—RPM or TPM—is hit first.

Columns

Product	API Endpoint	Description	w/o API Key	w/ API Key	w/ Premium API Key	Average Latency	Token Usage Counting	Allowed Request
Embedding API	`https://api.jina.ai/v1/embeddings`	Convert text/images to fixed-length vectors		500 RPM & 1,000,000 TPM	2,000 RPM & 5,000,000 TPM	depends on the input size	Count the number of tokens in the input request.	POST
Reranker API	`https://api.jina.ai/v1/rerank`	Tokenize and segment long text		500 RPM & 1,000,000 TPM	2,000 RPM & 5,000,000 TPM	depends on the input size	Count the number of tokens in the input request.	POST
Reader API	`https://r.jina.ai`	Convert URL to LLM-friendly text	20 RPM	200 RPM	1000 RPM	4.6s	Count the number of tokens in the output response.	GET/POST
Reader API	`https://s.jina.ai`	Search the web and convert results to LLM-friendly text		40 RPM	100 RPM	8.7s	Count the number of tokens in the output response.	GET/POST
Reader API	`https://g.jina.ai`	Grounding a statement with web knowledge		10 RPM	30 RPM	22.7s	Count the total number of tokens in the whole process.	GET/POST
Classifier API (Zero-shot)	`https://api.jina.ai/v1/classify`	Classify inputs using zero-shot classification		200 RPM & 500,000 TPM	1,000 RPM & 3,000,000 TPM	depends on the input size	Tokens counted as: input_tokens + label_tokens	POST
Classifier API (Few-shot)	`https://api.jina.ai/v1/classify`	Classify inputs using a trained few-shot classifier		20 RPM & 200,000 TPM	60 RPM & 1,000,000 TPM	depends on the input size	Tokens counted as: input_tokens	POST
Classifier API	`https://api.jina.ai/v1/train`	Train a classifier using labeled examples		20 RPM & 200,000 TPM	60 RPM & 1,000,000 TPM	depends on the input size	Tokens counted as: input_tokens × num_iters	POST
Segmenter API	`https://segment.jina.ai`	Tokenize and segment long text	20 RPM	200 RPM	1,000 RPM	0.3s	Token is not counted as usage.	GET/POST

Auto-recharge when tokens are low

Recommended for uninterrupted service in production. When your token balance is below the threshold you set, we will automatically recharge your credit card for the same amount as your last top-up. If you purchased multiple packs in the last top-up, we will recharge only one pack.

≤ 1M Tokens

Recharge if

With a commercial license for on-prem use

Require 100% control and privacy? Purchase a commercial license to use our models on-premises.

On-premises deployment

Deploy Jina Reranker on AWS Sagemaker and Microsoft Azure and soon in Google Cloud Services, or contact our sales team to get customized Kubernetes deployments for your Virtual Private Cloud and on-premises servers.

AWS SageMaker

Embeddings

Reranker

Microsoft Azure

Embeddings

Reranker

Google Cloud

Embeddings

Reranker

Performance Benchmark

Show benchmark for v2 model (latest)

MKQA (Multilingual Knowledge Questions and Answers)

Recall 10 scores reported for different reranking models for MKQA dataset

BEIR (Heterogeneous Benchmark on Diverse IR Tasks)

NDCG 10 scores reported for different reranking models for Beir dataset

ToolBench. The benchmark collects over 16 thousand public APIs and corresponding synthetically-generated instructions for using them in single and multi-API settings.

Recall 3 scores reported for different reranking models for ToolBench dataset

NSText2SQL

Recall 3 scores reported for different reranking models for NSText2SQL dataset

CodeSearchNet. The benchmark is a combination of queries in docstring and natural language formats, with labelled code-segments relevant to the queries.

MRR 10 scores reported for different reranking models for CodeSearchNet dataset

Throughput of Jina Reranker v2 on RTX4090

Throughput (documents retrieved in 50ms) scores reported for different reranking models on an RTX 4090 GPU.

Comparison of Reranker, Vector Search, and BM25

The table below provides a comprehensive comparison of the Reranker, Vector/Embeddings Search, and BM25, highlighting their strengths and weaknesses across various categories.

	Reranker	Vector Search	BM25
Best For	Enhanced search precision and relevance	Initial, rapid filtering	General text retrieval across wide-ranging queries
Granularity	Detailed: Sub-document and query segment	Broad: Entire documents	Intermediate: Various text segments
Query Time Complexity	High	Medium	Low
Indexing Time Complexity	Not required	High	Low, utilizes pre-built index
Training Time Complexity	High	High	Not required
Search Quality	Superior for nuanced queries	Balanced between efficiency and accuracy	Consistent and reliable for a broad set of queries
Strengths	Highly accurate with deep contextual understanding	Quick and efficient, with moderate accuracy	Highly scalable, with established efficacy
	Try reranker API for free	Try embedding API for free

Product	API Endpoint	Description	w/o API Key	w/ API Key	w/ Premium API Key	Average Latency	Token Usage Counting	Allowed Request
Embedding API	`https://api.jina.ai/v1/embeddings`	Convert text/images to fixed-length vectors		500 RPM & 1,000,000 TPM	2,000 RPM & 5,000,000 TPM	depends on the input size	Count the number of tokens in the input request.	POST
Reranker API	`https://api.jina.ai/v1/rerank`	Tokenize and segment long text		500 RPM & 1,000,000 TPM	2,000 RPM & 5,000,000 TPM	depends on the input size	Count the number of tokens in the input request.	POST
Reader API	`https://r.jina.ai`	Convert URL to LLM-friendly text	20 RPM	200 RPM	1000 RPM	4.6s	Count the number of tokens in the output response.	GET/POST
Reader API	`https://s.jina.ai`	Search the web and convert results to LLM-friendly text		40 RPM	100 RPM	8.7s	Count the number of tokens in the output response.	GET/POST
Reader API	`https://g.jina.ai`	Grounding a statement with web knowledge		10 RPM	30 RPM	22.7s	Count the total number of tokens in the whole process.	GET/POST
Classifier API (Zero-shot)	`https://api.jina.ai/v1/classify`	Classify inputs using zero-shot classification		200 RPM & 500,000 TPM	1,000 RPM & 3,000,000 TPM	depends on the input size	Tokens counted as: input_tokens + label_tokens	POST
Classifier API (Few-shot)	`https://api.jina.ai/v1/classify`	Classify inputs using a trained few-shot classifier		20 RPM & 200,000 TPM	60 RPM & 1,000,000 TPM	depends on the input size	Tokens counted as: input_tokens	POST
Classifier API	`https://api.jina.ai/v1/train`	Train a classifier using labeled examples		20 RPM & 200,000 TPM	60 RPM & 1,000,000 TPM	depends on the input size	Tokens counted as: input_tokens × num_iters	POST
Segmenter API	`https://segment.jina.ai`	Tokenize and segment long text	20 RPM	200 RPM	1,000 RPM	0.3s	Token is not counted as usage.	GET/POST

Do I need a commercial license?

CC BY-NC License Self-Check

Are you using our official API or official images on Azure or AWS?

Yes

Are you using a paid API key or free trial key?

Are you using our official model images on AWS and Azure?

	Number of tokens in each document
Number of tokens in the query	256	512	1024	2048	4096
64	156	323	1366	2107	3571
128	194	369	1377	2123	3598
256	273	475	1397	2155	4299
512	468	1385	2114	3536	7068

Reranker

Reranker API

What is a Reranker?

Three Ways to Purchase

On-premises deployment

Performance Benchmark

Comparison of Reranker, Vector Search, and BM25

Learning about Reranker

FAQ

How to get my API key?

What's the rate limit?

Do I need a commercial license?

Other questions