Skip to main content
Watch: I Built an AI App Without Leaving Databricks

Amazon Bedrock rerankers - verified

Amazon Bedrock reranker models

Amazon Bedrock: 2 reranker models, read from the provider's own pages on October 18, 2026. Amazon Bedrock rerankers are priced per 1,000 queries, from $1.00 per 1000 queries for Amazon Rerank 1.0.

Read from docs.aws.amazon.com, aws.amazon.com. Compare every reranker

Models
2
Current
2
Older
0
Open weights
0

Billing and caveats

Amazon Bedrock

Billing unit: query (up to 100 document chunks)

“A query is a single call to the reranker model that can contain up to 100 document chunks.”
docs.aws.amazon.com

Rerank billing unit (docs): "A query is a single call to the reranker model that can contain up to 100 document chunks." The Bedrock pricing footnote (checked 2026-10-18) says: "each document can only contain upto 512 tokens (inclusive of the query and document’s total tokens), and if the token length is higher than 512 tokens, it is broken down into multiple documents." It also says a request with 350 documents "will be treated as 4 queries."

Models

Amazon Rerank 1.0

amazon.rerank-v1:0 - API - Per 1,000 queries

GAinferred
Price (provider's unit)

$1.00 per 1000 queries

“Amazon-rerank-v1.0 · $1.00 per 1000 queries”
aws.amazon.com

Note: Bedrock defines a query as a call with up to 100 document chunks; larger requests count as multiple queries.

Status

GAinferred

“Amazon · Rerank 1.0 · amazon.rerank-v1:0”
Status inferred from - docs.aws.amazon.com
Context
Not stated
Documents per request

1,000

hard limit (sources array of the Bedrock Rerank API)

“Array Members: Minimum number of 1 item. Maximum number of 1000 items.”
docs.aws.amazon.com
Languages
Not stated
Open weights

No (API only) inferred

Note: Amazon first-party model on Bedrock; no open weights are listed in the sources checked.

Not available in us-east-1: "The Amazon Rerank 1.0 model is not supported in the US East (N. Virginia) AWS Region." Regions listed: ap-northeast-1, ca-central-1, eu-central-1, us-west-2. No context window or language count was found on the pages checked.

Cohere Rerank 3.5 (Bedrock)

cohere.rerank-v3-5:0 - API - Per 1,000 queries

GA
Price (provider's unit)

$2.00 per 1,000 queries

“Cohere models · Price per 1,000 queries**; Rerank 3.5 · $2.00”
aws.amazon.com

Note: Billed through AWS Marketplace under the model provider; a query can contain up to 100 document chunks.

Status

GA

“Model lifecycle: Active”
docs.aws.amazon.com
Context

4,000 tokens

context window (model card says 4K)

“Context window: 4K tokens”
docs.aws.amazon.com
Documents per request

1,000

hard limit (sources array of the Bedrock Rerank API)

“Array Members: Minimum number of 1 item. Maximum number of 1000 items.”
docs.aws.amazon.com
Languages
Not stated
Open weights

No (API only) inferred

Note: No official open weights are listed in the sources checked; the provider documents this as an API model.

Bedrock model card: launch date Dec 2, 2024; EOL no sooner than Dec 2, 2025; lifecycle Active. Regions include us-east-1.

FAQ

How much does Amazon Bedrock reranking cost?

Amazon Rerank 1.0: $1.00 per 1000 queries. Cohere Rerank 3.5 (Bedrock): $2.00 per 1,000 queries. Prices are in Amazon Bedrock's own units as of October 18, 2026. Billing unit: "A query is a single call to the reranker model that can contain up to 100 document chunks."

What is the context length of Amazon Bedrock rerankers?

Cohere Rerank 3.5 (Bedrock): 4,000 tokens, context window (model card says 4K). 1 model has no stated context length.

Can I run Amazon Bedrock rerankers myself?

No official open weights were found in the sources checked; Amazon Bedrock documents these as hosted models.

Sources

Last verified from each provider's own docs, pricing pages and Hugging Face cards; every quote was string-matched against the page that day. Prices are shown in the provider's own unit and change without notice, so check the linked source before you commit a budget.

Newsletter

Know when a reranker API changes

One email per week. New model releases, retrieval and pricing updates and what they mean for what you build.