bge m3
This model runs as a dedicated deployment on large GPUs and isn't in the shared playground by default. Get in touch and we'll set it up for you.
$ curl https://hostyourai.com/api/v1/embeddings \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "BAAI/bge-m3",
"input": "The quick brown fox"
}'
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
text->embedding · BAAI · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
- Router
- Router · on request
- Dedicated
- Dedicated · on request
Specifications
| Context window | 8,194 tokens |
|---|---|
| Architecture | XLMRobertaModel (vLLM) |
| License | mit |
| Modality | text->embedding |
| Released | January 2024 |
| Publisher | BAAI ↗ |
Pricing
Shared router · per token
Dedicated GPU · per hour
Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.
Bench index
Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.
Estimated from its size, fitted on every model on MTEB (its own scale).
Range 54.7 to 66.3
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 10-11-2026
Frequently asked questions
Can I run bge m3 in the EU?
Yes. HostYourAI runs bge m3 on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Is hosting bge m3 GDPR-compliant?
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.
How much does bge m3 cost?
bge m3 needs several GPUs at once, so it runs as a dedicated deployment billed per GPU minute rather than per token. Tell us your volume and we will work it out with you.
Is the API OpenAI-compatible?
Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.
More models from BAAI
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Request access
bge m3 isn't available by default yet. Leave your details and we'll arrange a dedicated deployment.
