Table of Contents [expand]
Last updated February 10, 2026
Amazon Rerank 1.0 is a reranking model that scores documents based on their semantic relevance to a query. It offers a reliable, high-performing solution that’s backed by AWS infrastructure.
- Model ID:
amazon-rerank-1-0 - Region:
us,eu
When to Use This Model
Amazon Rerank 1.0 is ideal for enhancing retrieval-augmented generation (RAG) systems and semantic search applications. You can use this model after retrieving results to identify the most relevant documents for your query.
Usage
Amazon Rerank 1.0 is available on our /v1/rerank API endpoint.
To provision access to the model, attach the inference addon to your app $APP_NAME:
heroku addons:create heroku-inference:standard -a $APP_NAME --as RERANK
Using config variables, you can invoke the model in a variety of ways:
- Heroku CLI
aiplugin (heroku ai:models:call) - curl
Rate Limits
- Maximum requests per minute: 200
Example curl Request
Get started quickly with an example request:
export RERANK_KEY=$(heroku config:get -a $APP_NAME RERANK_KEY)
export RERANK_URL=$(heroku config:get -a $APP_NAME RERANK_URL)
curl $RERANK_URL/v1/rerank \
-H "Authorization: Bearer $RERANK_KEY" \
-d @- <<EOF
{
"model": "amazon-rerank-1-0",
"query": "How do I configure SSL certificates for my domain?",
"documents": [
"Heroku automatically manages SSL certificates for applications using Automated Certificate Management.",
"You can view application logs in real-time using the heroku logs --tail command.",
"Custom domains require DNS configuration to point to your Heroku application.",
"SSL certificates encrypt traffic between clients and your application for secure communication."
],
"top_n": 2
}
EOF