Evaluating Amazon Bedrock Knowledge Base integration

Question

Amazon Bedrock Knowledge Base pricing is based on the following components:

---

1. Storage and Ingestion

• Storage: You are charged for the storage of vector embeddings in the underlying vector database (e.g., Amazon OpenSearch, Pinecone, or Redis Enterprise Cloud).
• Ingestion: When you ingest (sync) documents into the knowledge base, you are charged for the number of tokens processed to create embeddings.

Note: The actual storage and ingestion costs depend on the vector database you select. Bedrock itself does not charge a separate fee for the knowledge base feature, but you pay for the underlying vector store and the compute used for embedding generation.

---

2. Embedding Model Usage

• When you ingest documents, Bedrock uses an embedding model to convert your text into vectors.
• You are charged for the number of input tokens processed by the embedding model during ingestion.
• The price per 1,000 tokens depends on the embedding model you select (e.g., Amazon Titan Embeddings, Cohere Embed, etc.).

---

3. Vector Database (Vector Store) Costs

• You pay for the storage and retrieval operations in the vector database you choose (e.g., OpenSearch, Pinecone, Redis).
• These costs are billed separately by the respective service (e.g., OpenSearch Service pricing, Pinecone pricing, etc.).

---

4. Retrieval (Query) Costs

• When you query the knowledge base (e.g., via an agent), you are charged for:
  • The number of tokens processed by the embedding model (if your query is embedded).
  • The inference cost of the foundation model used to generate the answer (standard Bedrock model inference pricing).

---

Example Cost Flow

1. Ingest 10,000 tokens into the knowledge base:
   • Charged for 10,000 tokens by the embedding model.
   • Charged for storage in the vector database.
2. Query the knowledge base:
   • Charged for embedding the query (if applicable).
   • Charged for retrieval from the vector database.
   • Charged for the foundation model inference to generate the answer.

---

Where to See Pricing

• Amazon Bedrock Pricing
• Amazon OpenSearch Pricing
• Pinecone Pricing
• Redis Enterprise Cloud Pricing

---

Summary Table

Component	How Charged
Embedding Model	Per 1,000 tokens ingested/queried
Vector Database Storage	Per GB/month (varies by provider)
Vector Database Retrieval	Per query (varies by provider)
Model Inference	Per 1,000 tokens generated (standard Bedrock FM)

---

References:

• Amazon Bedrock Pricing
• Bedrock Knowledge Base Documentation
• S3 Data Source Connector