Sold by: Waltsoft Inc.
Deployed on AWS
BAAI BGE Base EN v1.5 on SageMaker. 768-dimensional embeddings scoring 63.55 on MTEB -- 95% of Large quality at $0.08/hr. The mid-tier for production RAG when cost and quality both matter.
Overview
BGE Base EN v1.5 from BAAI scores 63.55 on the MTEB benchmark -- just 0.68 points below the Large variant at one-third the memory footprint and roughly 3x the throughput on the same ml.m5.xlarge instance. It produces 768-dimensional L2-normalized vectors from inputs up to 512 tokens.
This is the production workhorse for RAG pipelines that need strong retrieval precision without the full cost of the Large model. At $0.08/hr it sits between BGE Small ($0.07/hr) and BGE Large ($0.10/hr), giving you a clear cost-quality ladder for different environments: Small for bulk ingestion, Base for production serving, Large for highest-precision search.
Drop-in compatible with all major vector stores: pgvector on Aurora/RDS, Amazon OpenSearch, Pinecone, Weaviate, Qdrant, Chroma, and Milvus. Integrates directly with LangChain (HuggingFaceBgeEmbeddings), LlamaIndex, and Haystack using the same configuration as the Large variant, switching only the model ID.
Primary use cases: production document retrieval for RAG, customer support knowledge base search, enterprise semantic search over internal wikis and documentation, product catalog similarity, and duplicate detection.
Highlights
- MTEB score 63.55 -- 95% of BGE Large precision at $0.08/hr, 3x throughput on the same ml.m5.xlarge instance
- 768-dimensional L2-normalized vectors, 512-token input -- drop-in for pgvector, OpenSearch, Pinecone, and Weaviate
- Runs in your own AWS VPC -- no external API calls, no token limits, no data leaving your account
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Real-Time) Recommended | Model inference on the ml.m5.xlarge instance type, real-time mode | $0.08 |
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $0.08 |
Vendor refund policy
No refunds.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial release
Additional details
Inputs
- Summary
BAAI BGE Base EN v1.5 on SageMaker. 768-dimensional embeddings scoring 63.55 on MTEB -- 95% of Large quality at $0.08/hr. The mid-tier for production RAG when cost and quality both matter.
- Input MIME type
- application/json
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
https://waltsoft-marketplace-assets.s3.amazonaws.com/ml-validation/text-sample/sample.jsonl
Support
Vendor support
Contact support@waltsoft.net for deployment assistance.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
BAAI BGE Small EN v1.5 on SageMaker. 384-dimensional embeddings, MTEB score 62.17, at $0.07/hr -- the budget tier for high-volume RAG ingestion and semantic search without per-token billing.
BAAI BGE Large EN v1.5 deployed as a private SageMaker endpoint. Scored 64.23 on MTEB, outperforming OpenAI Ada-002 (60.99) on retrieval tasks. Runs in your own AWS account -- no external API calls, no token limits.
New state-of-the-art neural text reranking model for 100+ languages
Mixedbread mxbai-embed-large-v1 on SageMaker. Scores 64.68 on MTEB -- beating OpenAI Ada-002 (60.99) and BGE Large (64.23). 1024-dimensional CLS embeddings, no per-token charges.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.