BAAIBGE M3
BGE-M3 is an embedding model developed by BAAI. It is designed for versatile retrieval, supporting dense, multi-vector, and sparse retrieval functionalities within a single model. It processes text inputs in over 100 languages and handles documents up to 8,194 tokens in length.
Input
Output
Context
8K
Max Output
n/a
Parameters
-
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
More models by BAAI
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about BGE M3
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
BGE M3 advertises a context window of 8,194 tokens. The figure is the creator's published maximum; a given provider may serve less, and the gateway routes on what each provider actually serves.
Yes. BGE M3 is an open-weight model released under the MIT license, so the weights can be downloaded and self-hosted within that license's terms.
BGE M3 accepts Text and produces Embedding. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for BGE M3 is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; BGE M3 is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
BAAI has not published a parameter count for BGE M3, so the catalog cannot estimate its memory footprint. The capacity planner can size it from a parameter count you supply.
Fields collected from public registries, provider APIs and benchmark publishers, each tagged with its source.
Last updated: Oct 15, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start on the free plan with 5,000 requests a month, no card required.