Using BGE Reranker V2 M3 on Novita AI

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

ServerlessOpen Source

Novita AI exposes BGE Reranker V2 M3 through model ID bge-reranker-v2-m3. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Novita AI and generate an API key.
  2. 2
    Use the Novita AI SDK or REST API to call bge-reranker-v2-m3.
  3. 3
    You'll be billed $0.01/1M input. See full pricing.
API PortalPricingModel Card

Code Examples

Code examples for this provider have not been sourced yet.

Pricing on Novita AI

TypePrice (per 1M)
Input tokens$0.01

Capabilities

No model capability flags are currently sourced.

About BGE Reranker V2 M3

BGE Reranker V2 M3 is BAAI's lightweight multilingual cross-encoder reranking model from the FlagEmbedding project, based on the BGE-M3 backbone. Accepts query-passage pairs and outputs direct relevance scores. Supports multi-lingual processing with 568 million parameters. Part of the BGE reranker v2 series released March 2024 alongside LLM-based rerankers.

Full model details →

Model Specs

Released2024-03-18
Parameters568M
Context8k
ArchitectureEncoder Only

More Models on Novita AI

BGE M3
All models on Novita AI →

Provider

Novita AI