Rerank API
Reorder retrieved documents by relevance to a query before they reach your LLM. The Eden AI Rerank API follows the Cohere v2 format and gives you 16 reranker models from 9 providers behind one API key.
Trusted by 500+ Companies, from Startups to Industry Leaders
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
.png)
How to rerank documents with Eden AI?
What is a Rerank API?
A rerank API takes a query and a list of documents and returns the documents sorted by relevance, each with a score. It runs after a first retrieval step, such as vector search with embeddings or keyword search, which is fast but approximate. A reranker reads the query and each document together, so it catches matches that embeddings miss and puts the best passages at the top of the context you send to an LLM. Fewer, better passages mean more accurate answers and fewer input tokens.
Add Reranking to Your RAG Pipeline in One Call
Retrieve 20 to 100 candidates with keyword search or vector search on embeddings, send them to POST /v3/rerank with the user's query, and keep the top results for your prompt. The request and the response follow the Cohere v2 rerank API, so an existing Cohere client works by changing the base URL and the model id.
Each result gives the index of a document and its relevance score, sorted from best to worst. The password article comes first, the 2FA guide second. The response also reports what the call cost.
.avif)
16 Reranker Models From 9 Providers, One Bill
Call rerankers from Google Vertex AI, Amazon Bedrock, Qwen, Alibaba Cloud, DeepInfra, Fireworks AI, GreenPT, IONOS and Infomaniak with the same API key. Each model is priced either per query or per token, at the provider's rate. Nine models run in an EU region and also answer on the Eden AI EU endpoint.
Open the Rerank catalog in the Eden AI app to see every reranker model with its provider, price and region, and filter by EU hosting or zero data retention. Then run the same query and documents through two or three models to see which ranking fits your data.
Value delivered
Save time
Integrate once and access hundreds of models without managing multiple APIs.
Model updates, provider changes, and new releases are handled transparently.
Reduce costs
Use the most efficient model for each need. Avoid vendor lock-in and adapt quickly to pricing or performance changes.
Reduce risk
Built-in fallback mechanisms protect applications from model outages. Routing flexibility allows rapid adaptation to evolving technologies and providers.
They are using Rerank API
Got specific needs? We're here to help
AI API Gateway
5.5% platform fee
Advanced AI Platform
Custom price
Other features
Ask typed questions about a text, such as which team, how urgent, or yes or no, and get a choice, a score or a probability back instead of prose. One request answers many questions at once, and only input tokens are billed. This endpoint is in alpha.
Unlock the power of data privacy with our Data Anonymization API. Effortlessly protect sensitive information while maintaining data integrity for your applications.
Unlock the power of emotion detection with our AI API. Effortlessly analyze and interpret emotions from facial expressions to enhance user experiences and drive engagement.
Start building with Eden AI
A single interface to integrate the best AI technologies into your products.