by Baai · Released 2025-11-18
The bge-m3 embedding model encodes sentences, paragraphs, and long documents into a 1024-dimensional dense vector space, delivering high-quality semantic embeddings optimized for multilingual retrieval, semantic search, and large-context applications.
What this model can take in, what it replies with, and what it does not do.
You call one endpoint. Behind it, OpenDunes keeps every one of these live — if one degrades, the next takes the request without you changing a line.
Routed through the Bifrost gateway · prices in Algerian Dinars per 1M tokens · you’re charged the price of the endpoint that served your request.
Each request charges exactly what it uses — no subscription, no minimum.
3 000 DA ≈ 3 083 247 typical replies · the exact charge appears after every request, down to the centime.
OpenAI-compatible — point any OpenAI SDK at our base URL and keep your code. Copy the request, or run it right here on your wallet.
Sign in to run this request on your own wallet.
The same request, in your language
Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.
The hard numbers — what it can take in, what it can give back, and where it stops.
3,24 DA for the text you send and Free for the text it writes back. A typical exchange — a short question and a one-screen answer — costs about 0,001 DA. You pay for what you actually use: no subscription, no minimum.
bge-m3 reads up to 8K tokens in one request, and writes back up to roughly 6,000 words at once.
It reads text and replies with embeddings. It also supports replying in structured JSON.
Yes. Top up your OpenDunes balance in dinars with a CIB or Edahabia card, then spend it on bge-m3 or any other model in the catalog from that same balance. No foreign card, no currency conversion, no subscription.
bge-m3 is built by Baai, released on Nov 18, 2025. OpenDunes serves it unchanged — same model, same weights, billed in dinars.