Using BGE Reranker Base on Cloudflare Workers AI

Implementation guide · BGE · Beijing Academy of Artificial Intelligence (BAAI)

ServerlessOpen Source

Cloudflare Workers AI exposes BGE Reranker Base through model ID @cf/baai/bge-reranker-base. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-03. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cloudflare Workers AI and generate an API key.
  2. 2
    Use the Cloudflare Workers AI SDK or REST API to call @cf/baai/bge-reranker-base — see the documentation for request format.
  3. 3
    You'll be billed $0.00/1M input. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Cloudflare Workers AI documentation for integration details.

Pricing on Cloudflare Workers AI

TypePrice (per 1M)
Input tokens$0.00

Capabilities

No model capability flags are currently sourced.

About BGE Reranker Base

BGE Reranker Base is BAAI's cross-encoder reranking model for query-document relevance scoring in retrieval pipelines. It reranks candidate passages after first-stage retrieval and is available through Cloudflare Workers AI.

Full model details →

Model Specs

Released2023-09-12
Context512
ArchitectureEncoder Only

More Models on Cloudflare Workers AI

BGE M3BGE Large EN v1.5BGE Base EN v1.5BGE Small EN v1.5
All models on Cloudflare Workers AI →

Provider

Cloudflare Workers AI

Cloudflare

San Francisco, California, United States