GPT-6.2 Astra, GPT-6.2 Sol and Kimi K3.1 Pro are now live. Try them now
Back to Models
Beijing Academy of AI

BGE M3

by baai

Embedding

Description

BGE M3 is BAAI's multilingual embedding model for dense, sparse, and multi-vector retrieval with long-context inputs.

Providers

Pricing

Provider prices for BGE M3
ProviderPrice
IONOS CloudInput: USD 0.02 / 1M tokensOutput: USD 0 / 1M tokens
Nebulfp16Input: EUR 0.12 / 1M tokensOutput: EUR 0.6 / 1M tokens
OVHcloudfp16Input: EUR 0.01 / 1M tokensOutput: EUR 0 / 1M tokens
Get Your API Key

Specifications

Context8K tokens
Parameters—
License—
ReleasedJan 2024

Capabilities

EU-Compliant API Access

Use BGE M3 with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.ai/api/v1/embeddings \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bge-m3",
    "input": "EUrouter only routes to EU-hosted providers."
  }'

More from baai

Beijing Academy of AI

BGE Multilingual Gemma2

Input: EUR 0.01 / 1M tokensOutput: EUR 0 / 1M tokens

Beijing Academy of AI

BGE Reranker v2 M3

Input: EUR 0.1 / 1M tokens

Explore more

Integrate AI without GDPR risk.

You need AI that won’t create compliance headaches. Your data stays in the EU, GDPR is enforced by default, and every request is routed for the best balance of cost, latency, and uptime, reducing risk while improving performance.

Get Your API Key
GDPR by default
EU data residency
Smart routing