BGE Reranker v2 M3

by BAAI (Beijing Academy of AI)Rerank

Reranking model for improving retrieval quality in search and recommendation systems

Context
8.2K tokens
Max output
1 tokens
Parameters
0.57B total
Released
2024-03-12
Weights
Open
Licence
apache-2.0

Weights on Hugging Face

baai/bge-reranker-v2-m3

Specifications

Full facts as recorded, incl. what is unknown.

Released
2024-03-12
Weights
Opennot gated
License
apache-2.0
Input
Text
Output
Rerank
Context window
8,192 max across endpoints
Max output
1
Providers
2
Epoch Capabilities Index
not evaluated
Direct price range
no comparable direct price
More details
Last updated
2026-04-30
Knowledge cutoff
Weights link
Hugging Face · BAAI/bge-reranker-v2-m3
Parameters
0.57B total

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Cost calculator

Loading endpoints…

More from BAAI (Beijing Academy of AI)

Newest BAAI (Beijing Academy of AI) models in the catalogue. All BAAI (Beijing Academy of AI) models

ModelReleasedContextListed price
bge-base-en-v1.52025-11-18512from $0.008 /1M tok
bge-large-en-v1.52025-11-18512$0.01 via OpenRouter
BGE Multilingual Gemma22024-07-258.2Kfrom $0.08 /1M tok
BGE M32024-01-308.2Kfrom $0.01 /1M tok
bge-en-icl—32.8Kfrom $0.01 /1M tok
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model