BGE Reranker v2 M3
BGE Reranker v2 M3 is a reranking model from BAAI, suited to reranking search results. It runs with an 8K-token context window.
Specifications
- Provider
- BAAI
- Type
- Reranking model
- Category
- Text
- Context window
- 8K tokens
- License
- apache-2.0
- API endpoint
- /v1/embeddings
- Model ID
- bge-reranker-v2-m3
About BGE Reranker v2 M3
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
Hugging Face · 14,648,377 downloads · 1,302 likes
BGE Reranker v2 M3 API example
Embeddings through the OpenAI-compatible Denizen Blu One API. Point any OpenAI SDK at api.denizenblu.com/v1, set model to bge-reranker-v2-m3 and send the request.
curl https://api.denizenblu.com/v1/embeddings \
-H "Authorization: Bearer $DENIZEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "bge-reranker-v2-m3",
"input": "Flat-rate AI for every team."
}'Need keys, streaming or error codes? See the API docs, or try it first in the playground.
Included in every plan
BGE Reranker v2 M3 is part of the flat-rate catalog, so you never pay per token to use it. Plans differ by usage limits, concurrency and support, not by whether this model is available.
- Explorer$11 a year
- Creator$31 a year
- Professional$51 a year
- Ultimate$101 a year
- EnterpriseContact sales