Amazon Bedrock Titan Embeddings v2
41/100AWS-hosted Titan Text Embeddings V2 via the Bedrock API.
aws.amazon.com// scorecard · 41/100
verified 1mo agoAgent-readiness11/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server0/9
llms.txt0/3
Reliability & performance0/15
Actively maintained—
Production-ready0/4
Updated recently—
Pricing6/13
Itemized public pricing6/6
Free tier / trial0/4
Free-tier generosity—
Docs & DX10/12
Docs quality8/8
Public API2/2
Quickstart / examples0/2
Security & compliance10/12
SOC 26/6
ISO 270012/2
GDPR2/2
Security / trust page0/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size—
Years operating—
// rankings · cost per standard workload
#7 in Embeddings$2/ 100M tokens
Titan V2 on-demand $0.02/1M tokens x100 = $2/mo
aws.amazon.com/bedrock/pricing// overview
Amazon Titan Text Embeddings V2 is a Bedrock embeddings model converting up to 8,192 tokens of text into vectors of 1,024, 512, or 256 dimensions. Optimized for RAG and document search; supports semantic similarity, reranking, classification, and clustering.
Best for: Cost-efficient embeddings for RAG on AWS with flexible vector dimensions
// pricing
Free tier
Includes:
Limits:
On-demand$0.02/1M tokens
- Pay-per-use on Bedrock
// security & compliance
✓ SOC 2✓ ISO 27001✓ GDPR✓ HIPAA
// features
- 1024/512/256-dim outputs (512 keeps ~99% accuracy)
- 8,192-token / 50k-char input
- Normalize flag (default true)
- float and binary embedding types
- 100+ languages + code
- On-demand or Provisioned Throughput