Our Embedding Models
Here's an overview of our current model lineup:
| Model Card | Context Length | Dimension | MTEB Average |
|---|---|---|---|
| mxbai-embed-large-v1 | 512 | 1024 | 64.68 |
| mxbai-embed-2d-large-v1 | 512 | 1024 (base) | 63.25 (base) |
| deepset-mxbai-embed-de-large-v1 | 512 | 1024 | - |
| mxbai-embed-xsmall-v1 | 4096 | 384 | 42.80 |
Why Choose Mixedbread Embeddings
The Mixedbread embed family offers several advantages:
- Powerful Performance: State-of-the-art results on benchmarks
- Size Efficiency: Optimized for resource utilization
- Open-Source: Fully accessible and customizable
- Versatility: Suitable for various NLP tasks
Performance Comparison
Our new mxbai-embed-large-v1 model outperforms other similarly sized open models and even surpasses some closed-source models on the MTEB benchmark:
| Model | Avg (56 datasets) |
|---|---|
| mxbai-embed-large-v1 | 64.68 |
| bge-large-en-v1.5 | 64.23 |
| jina-embeddings-v2-base-en | 60.38 |
| OpenAI text-embedding-3-large (Proprietary) | 64.58 |
| Cohere embed-english-v3.0 (Proprietary) | 64.47 |
API Benefits
While you can use our open-source models directly, our API offers additional advantages:
- Enhanced Performance: API-exclusive versions offer improvements like better int8-quantization and take advantage of our optimized inference pipeline.
- Calibration Data: Generated using over 50 million samples for more accurate float32 to int8 mapping
- Faster Response Times: Optimized for low-latency retrieval tasks
Billing
Information related to billing
mxbai-embed-large-v1
Discover mxbai-embed-large-v1, our state-of-the-art English embedding model. Learn about its powerful performance, versatility across various NLP tasks, and how to effectively use it for semantic search, information retrieval, and other applications.
Last updated: July 14, 2025