Sold by: Cohere
Deployed on AWS
Rerank 5 Pro is Cohere's most advanced reranking model yet, leading major public benchmarks on complex enterprise retrieval and pinpointing the passages that matter within each document, so your LLM gets the right context with fewer tokens.
Overview
Every token your LLM reads is a token you pay for, and retrieval decides which tokens those are. Rerank 5 Pro is Cohere's most advanced reranking model yet. It reads each query alongside the results from your existing keyword, vector or hybrid search and puts the most relevant first, so your AI applications get the right context for every request. New in Rerank 5, Context Focus also returns the passages within each document that answer the query, in the same call. That means more accurate answers, fewer wasted LLM tokens, and better end-user experiences.
Rerank 5 Pro is for workloads where ranking quality decides the outcome: complex or reasoning-heavy queries, long domain-specific documents, and any step whose results feed an LLM answer, an expert's decision or a compliance outcome. Fact-check credit memos against filings, verify the citations in a legal brief, match patient cases to payer-policy criteria, or give research agents the right evidence at every step. For high-volume, latency-sensitive traffic, pair it with Rerank 5 Fast, which uses the same request and response format.
Key specifications:
- 32K-token context window for long documents
- Context Focus returns scored relevant passages in the same call (opt-in)
- Calibrated relevance scores that read as probabilities
- Supports 100+ languages, including cross-language search
- Reranks text and semi-structured data such as JSON, tables and code
- Works after any keyword, vector or hybrid search, with no re-indexing
- Runs in your own AWS account, so your data stays in your environment
Highlights
- State-of-the-art reranking. Rerank 5 Pro leads major public benchmarks including ViDoRe V3, BEIR, BRIGHT and nanoMTEB. Domain-wise, its excels on reasoning-intensive retrieval, financial tasks, life sciences, and parsed visual documents.
- Passage-level precision with Context Focus. New in Rerank 5, Context Focus returns the most relevant passages within each document, in the same Rerank call. Send only that evidence to your LLM to cut token costs and latency, with no extra pipeline step. It works like a dial: trim context with minimal loss in answer quality, or go further when savings matter most.
- Scores you can act on. Rerank 5 Pro's relevance scores are calibrated out of the box: a score of 0.7 means a 70% chance the document is useful. Set one threshold and pass every document above it to your LLM, instead of a fixed top-k. When nothing clears the bar, an agent can search again or say it doesn't know. One threshold works across domains and alongside Rerank 5 Fast.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g5.xlarge Inference (Batch) Recommended | Model inference on the ml.g5.xlarge instance type, batch mode | $4.55 |
ml.p5.4xlarge Inference (Real-Time) Recommended | Model inference on the ml.p5.4xlarge instance type, real-time mode | $4.55 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $3.12 |
Dimensions summary
You pay by the hour for each instance you run, based on the compute type and inference mode. The ml.g5.xlarge option runs in batch mode, which processes grouped requests. The ml.p5.4xlarge and ml.p4d.24xlarge options run in real-time mode, which returns results as requests arrive. Pricing scales with the instance you choose and how many hours it stays active. You can combine instances to match your throughput needs. No long-term commitment applies; you pay only for the hours each instance runs.
Top-of-mind questions for buyers
One host-hour is one running instance active for one hour. You pay for each hour an instance stays running, regardless of how many requests it processes. Stopping an instance ends software charges. Idle but running instances still accrue hourly charges, so stop instances you are not using.
The ml.g5.xlarge runs batch mode, which processes grouped requests together, suited to large jobs without strict timing needs. The ml.p5.4xlarge and ml.p4d.24xlarge run real-time mode, returning rankings as each request arrives, suited to interactive search. All three bill per running host-hour.
Each instance bills independently at its own hourly rate for every hour it runs. Running several instances adds those hourly charges together on the same invoice. Your total depends on which instance types you choose and how long each stays active. You can mix batch and real-time instances.
docs.cohere.com
Helpful?
Vendor refund policy
No refunds available.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Reliability fix for Rerank 5 Pro. Resolves a rare inference error under higher load. Model quality, scores, and the API are unchanged.
Additional details
Inputs
- Summary
The model accepts JSON requests that specify a query and the list of documents to be reranked. The maximum number of documents that can be passed into a single rerank call is 1,000. The documentation below is for Version 2 of the Rerank API.
{"model": "...", "query": "...", "documents": ["..."], "top_n": 10}
Context Focus (opt-in, off by default): add relevant_spans, for example "relevant_spans": {"mode": "enabled", "threshold": 0.3, "max_spans": 10}.
- Limitations for input type
- Text input only. Real-time inference only; batch transform is not supported. Send at most 1,000 documents per request. The query and each document share a 32,768-token context window. Documents that exceed it are split into chunks and scored per chunk, and the highest chunk score is returned. Format structured data such as JSON or tables as YAML strings and keep key order consistent (in Python, yaml.dump(doc, sort_keys=False)), because long documents are truncated. Rerank 5 does not support instructions that change how relevance is judged. Context Focus works best for targeted queries: broad requests such as summarization need the full document, and tables, forms and code split less cleanly than prose. TBC: confirm whether max_tokens_per_doc is supported for Rerank 5 on SageMaker (and its default and maximum), and the query token limit.
- Input MIME type
- application/json
Text input only. Real-time inference only; batch transform is not supported. Send at most 1,000 documents per request. The query and each document share a 32,768-token context window. Documents that exceed it are split into chunks and scored per chunk, and the highest chunk score is returned. Format structured data such as JSON or tables as YAML strings and keep key order consistent (in Python, yaml.dump(doc, sort_keys=False)), because long documents are truncated. Rerank 5 does not support instructions that change how relevance is judged. Context Focus works best for targeted queries: broad requests such as summarization need the full document, and tables, forms and code split less cleanly than prose. TBC: confirm whether max_tokens_per_doc is supported for Rerank 5 on SageMaker (and its default and maximum), and the query token limit.
Batch transform unavailable.
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Rerank improves search systems by sorting documents based on their semantic similarity to a query.
Rerank improves search systems by sorting documents based on their semantic similarity to a query. Choose fast, when you need a fast Reranking model. Choose pro, when you need the Reranking model with the best performance.
Rerank improves search systems by sorting documents based on their semantic similarity to a query. Choose fast, when you need a fast Reranking model. Choose pro, when you need the Reranking model with the best performance.
Rerank will return a sorted list of documents based on the semantic similarity between the query and documents.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.