BGE-M3
Open Multilingual Multifunction Embeddings
Beijing Academy of AI's January 2024 embedding model — supports 100+ languages and produces dense, sparse, AND multi-vector outputs from a single forward pass. The de facto open embedding model for multilingual RAG; widely deployed and forked.
Cost
Free
Open weights — self-host
Context
8K
Up to 8,192 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on
Artificial Analysis. Cost buckets are fixed dollar
thresholds keyed off output-token price ($/M out).
Intelligence
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
Speed
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
Cost
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
Made high-quality multilingual embeddings free and self-hostable. Combined with BGE-Reranker v2-m3, the BGE stack is the open RAG backbone for languages other than English.
Core Capabilities
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Research
Foundational paper or scientific contribution.
Context Window
8k tokens
≈ short doc
4k Chat 聊天
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
8k
Availability
API
Not available
Product / App
Not available
Open Source
Released
Enterprise
—
Pricing Model
Free / self-host
Open weights — pay only for compute.
Self-host What it feels like
- Language model from BAAI — see the linked sources below for benchmark and review coverage
Best use cases
- General-purpose tasks within BAAI's deployment footprint
- See the model spec and sources block for benchmarked use cases
Not ideal for
- Tasks far outside the modalities listed in this model's spec
- Workflows where a more recent successor in the same family scores higher