LLM Reference

BGE M3

Released
2024-01-27
Last refreshed
2026-05-22
Status
Researched 45d ago
Open SourceCommercial use allowed

BGE M3 is worth evaluating for general LLM work when its provider route and context window match the workload.

Use it for

  • Teams evaluating general LLM work
  • Workloads that can use a 8k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
  • Strict JSON or tool-calling flows
Specifications
Family
BGE
Released
2024-01-27
Context
8k
Parameters
568M
Architecture
encoder
Specialization
embedding
Openness
Open source
License
MIT(OSI)Commercial use allowed
Training
pretrained
Created by

Open-source AI fostering global collaboration

Beijing, China
Founded 2018
Website
Pricing
Output / 1M
-
Input / 1M
$0.010

Cheapest of 2 routes · Novita AI

About

BGE-M3 is BAAI's flagship multilingual embedding model that simultaneously performs dense retrieval, sparse (lexical) retrieval, and multi-vector (ColBERT-style) retrieval. It covers 100+ languages with an 8,192-token context window — far longer than most embedding models — making it effective for both short queries and long documents. Built on an extended XLM-RoBERTa architecture, it achieves state-of-the-art results on the MKQA and MLDR multilingual retrieval benchmarks and is available via NVIDIA NIM.

BGE M3 is an open-source model in the BGE family. The structured metadata tracks a 8k-token context window. This page tracks provider routes through Cloudflare Workers AI and Novita AI. No headline benchmark score is tracked for BGE M3 yet.

Top use-case fit

No primary decision-task fit is mapped for this model yet.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Novita AI$0.010-
ServerlessPartial
Cloudflare Workers AI--
ServerlessPartial

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.