Docs
Get an API key

BGE M3 bge-reranker-v2-m3

Multilingual reranker that scores query-document relevance with an 8K-token input window. Input longer than the context length is silently truncated by the engine and billed as truncated, not rejected.

From the live catalog
View .md
Tokens
$0.05 / 1M tokens
Context
8K tokens
region SJC quantization fp16 Hugging Face BAAI/bge-reranker-v2-m3

Inputs

InputAccepts
text
context 8K tokens

Parameters

ParameterTypeValuesDefault
top_ninteger1–100
return_documentsboolean

Endpoints

A request

curl https://api.vultrinference.com/v1/rerank \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-reranker-v2-m3",
    "query": "What is the capital of France?",
    "documents": [
      "Berlin is the capital of Germany.",
      "Paris is the capital of France."
    ],
    "top_n": 1
  }'