Reranker
Maximize the search relevancy and RAG accuracy with our cutting-edge reranker API. Start with 1M free tokens.
Interested in fine-tuned rerankers tailored to your data and use case? Let's discuss!
Reranker API
Try our cutting-edge reranker API to maximize your search relevancy and RAG accuracy. Starting for free!
upload
Request
curl https://api.jina.ai/v1/rerank \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $JINA_API_KEY" \
-d '{
"model": "$MODEL_NAME",
"query": "Organic skincare products for sensitive skin",
"documents": [
"Eco-friendly kitchenware for modern homes",
"Biodegradable cleaning supplies for eco-conscious consumers",
"Organic cotton baby clothes for sensitive skin",
"Natural organic skincare range for sensitive skin",
"Tech gadgets for smart homes: 2024 edition",
"Sustainable gardening tools and compost solutions",
"Sensitive skin-friendly facial cleansers and toners",
"Organic food wraps and storage solutions",
"All-natural pet food for dogs with allergies",
"Yoga mats made from recycled materials"
],
"top_n": 3
}'
download
Response
{
"model": "undefined",
"usage": {
"total_tokens": 38,
"prompt_tokens": 38
},
"results": [
{
"index": 3,
"document": {
"text": "Natural organic skincare range for sensitive skin"
},
"relevance_score": 0.8292155861854553
},
{
"index": 2,
"document": {
"text": "Organic cotton baby clothes for sensitive skin"
},
"relevance_score": 0.14426936209201813
},
{
"index": 6,
"document": {
"text": "Sensitive skin-friendly facial cleansers and toners"
},
"relevance_score": 0.13857832551002502
}
]
}
Available tokens
0
API Pricing
Our API pricing is structured around the quantity of tokens sent in the requests. This pricing model is applicable to both embedding and reranking APIs. With the same API key, you have access to both services.
Top up this API key by selecting the tokens you need
1M free tokens
Please input the right API key to top up
Performance Benchmark
For comparison, we included three other leading rerankers by BGE (BAAI), BCE (Netease Youdao), and Cohere in the benchmark. As shown by the results below, Jina Reranker holds the highest average score in all relevant categories for reranking, making it a clear leader among its peers.
LlamaIndex
LlamaIndex assessed various combinations of embeddings and rerankers for RAG, conducting a replication study that measured the Mean Reciprocal Rank. The findings highlight the Jina Reranker's significant enhancement of search quality, a benefit that is independent of the specific embeddings used.
BEIR
BIER (Benchmarking IR) assesses a model's retrieval effectiveness, including relevance and NDCG. A higher BIER score correlates to more accurate matches and search result rankings.
LoCo
Through the LoCo benchmark, we measured a model's understanding of local coherence and context, together with query-specific ranking. A LoCo higher score reflects a better ability to identify and prioritize relevant information.
MTEB
The MTEB (Multilingual Text Embedding Benchmark), on the whole, tests a model’s abilities in text embeddings, including clustering, classification, retrieval, and other metrics. However, for our comparison, we only used the MTEB’s Reranking tasks.
Get up to 5x speedup with reranker-turbo
We also offer two new open-source reranker models: jina-reranker-v1-turbo-en and jina-reranker-v1-tiny-en, the latter has only 30M parameters and four layers. These two new rerankers enjoy 5X faster inference speed than the base model at only a very small cost on the quality. They are perfect for applications that require real-time reranking. Read the benchmark below.
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.
Learning about Reranker
What is a reranker? Why is vector search or cosine similarity not enough? Learn about rerankers from the ground up with our comprehensive guide.
FAQ
At any time, press
/
to open search barReranker-related common questions
How much does the Reranker API cost?
What is the difference between the two rerankers?
Is Jina Reranker open source?
Does the reranker support multiple languages?
What is the maximum length for queries and documents?
What is the maximum number of documents I can rerank per query?
What is the batch size and how many query-document tuples can I send in one request?
What latency can I expect when reranking 100 documents?
Can I deploy Jina Reranker on AWS?
Do you offer a fine-tuned reranker on domain-specific data?
API-related common questions
code
Can I use the same API key for both the embedding and reranking APIs?
code
Can I monitor the token usage of my API key?
code
What should I do if I forget my API key?
code
Do API keys expire?
code
Why is the first request for some models slow?
code
Is user input data used for training your models?
Billing-related common questions
attach_money
Is billing based on the number of sentences or requests?
attach_money
Is there a free trial available for new users?
attach_money
Are tokens charged for failed requests?
attach_money
What payment methods are accepted?
attach_money
Is invoicing available for token purchases?