Model Library/baai/bge-reranker-v2-m3

baai/bge-reranker-v2-m3

by BAAI

Input price: $0.01/ M tokens
Output price: $0.01/ M tokens
Context window: 8Ktokens
Max output: 8Ktokens

baai/bge-reranker-v2-m3 is a lightweight multi-language re-ranking model. Developed based on the bge-m3 model, it has strong multilingual capabilities, ease of deployment, and fast inference speed. This model takes query and document as input and directly outputs a similarity score, rather than an embedding vector. It is well-suited for multi-language scenarios, particularly excelling in Chinese and English processing.

Features

Serverless API

Docs

baai/bge-reranker-v2-m3 is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.

Available Serverless

Run queries immediately, pay only for usage

Input$0.01 / M Tokens

Output$0.01 / M Tokens

Get your API key
Sign up and create a key to run the code below. The API is OpenAI-compatible.
Log in Get your API key

Make your first request

The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.

Base URL: https://api.novita.ai/openai
Model ID: baai/bge-reranker-v2-m3
API Endpoint: rerank

1import requests
2
3url = "https://api.novita.ai/openai/v1/rerank"
4headers = {
5    "Authorization": "Bearer <Your API Key>",
6    "Content-Type": "application/json"
7}
8payload = {
9    "model": "baai/bge-reranker-v2-m3",
10    "query": "What is the capital of France?",
11    "documents": [
12        "Paris is the capital of France.",
13        "Berlin is the capital of Germany."
14    ],
15    "top_n": 2
16}
17
18response = requests.post(url, headers=headers, json=payload)
19print(response.json())