Rerank 5 Fast

Use it to rank documents in high-volume or latency-sensitive search and retrieval workflows.

Availability

Rerank API, Microsoft Foundry, Amazon SageMaker, and Model Vault

Pricing model

Standard Vault pricing

Deployment

Private deployments in your own VPC or on-premises available by contacting sales

Privacy

Not established

Licence

Not established

• Rerank 5 Fast is optimized for low latency and high throughput, particularly for high-volume search and agents that run many searches per task. ^{[1] [2]}

  rerank-v5.0-fast : Optimized for low latency and high throughput, particularly for high-volume search and agents that run many searches per task.

• Rerank 5 Fast outperforms the previous-generation Rerank 4 Pro model. ^{[1] [2]}

  Rerank 5 Fast brings that quality to latency- and cost-sensitive workloads, and outperforms our previous-generation Rerank 4 Pro model.

• Rerank 5 supports over 100 languages and has a 32k-token context window.
• Context Focus can return relevant passages within each document as scored character spans in the same Rerank call.
• Rerank 5 Fast is available through the Rerank API, Microsoft Foundry, Amazon SageMaker, and Cohere Model Vault. ^[2]