Last refreshed 2026-05-22. Next refresh: weekly.
Why use BGE M3 on Novita AI?
Novita AI offers BGE M3 with pay-as-you-go pricing at $0.01/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: bge-m3bge-m3Request example
Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.01 |
Capabilities
No model capability flags are currently sourced.
About BGE M3
BGE-M3 is BAAI's flagship multilingual embedding model that simultaneously performs dense retrieval, sparse (lexical) retrieval, and multi-vector (ColBERT-style) retrieval. It covers 100+ languages with an 8,192-token context window — far longer than most embedding models — making it effective for both short queries and long documents. Built on an extended XLM-RoBERTa architecture, it achieves state-of-the-art results on the MKQA and MLDR multilingual retrieval benchmarks and is available via NVIDIA NIM.
FAQ
What is the context window for BGE M3 on Novita AI?
BGE M3 supports a 8,192 token context window on Novita AI.
What API model ID do I use for BGE M3 on Novita AI?
Use the model ID bge-m3 when calling Novita AI's API.
Who created BGE M3?
BGE M3 was created by Beijing Academy of Artificial Intelligence (BAAI) as part of the BGE model family.
Is BGE M3 open source?
BGE M3 is open source according to the seed data.