Embedding & Reranking
Embedding Models
| Model Name | Model ID | Dimensions | Max Context |
|---|---|---|---|
| BGE-m3 | bge-m3 | 1024 (fixed) | 8K tokens |
| Qwen3-VL-Embedding 8B | qwen3-vl-embedding-8b | 128 – 4096 (configurable) | 32K tokens |
Qwen3-VL-Embedding 8B
Multimodal embedding model supporting text, image, and mixed inputs. Compatible with Cohere's query/document differentiation on the embed endpoint for improved retrieval.
Supported dimensions: 128, 256, 384, 512, 768, 1024, 1536, 2048, 2560, 3072, 3584 and 4096.
Reranking Model
| Model Name | Model ID | Description |
|---|---|---|
| BGE-Reranker-v2-m3 | bge-reranker-v2-m3 | Classifies and re-scores embeddings from a vector database on each RAG query |