Titan Embed Text V2
Titan Embed Text V2 is Amazon's text embedding model for search and retrieval workloads, available through Amazon Bedrock and now via the Vercel AI Gateway. It produces embeddings optimized for semantic similarity and document retrieval within AWS-native applications.
Titan Embed V2 is particularly well-suited for organizations already invested in the AWS ecosystem, offering seamless integration with Amazon OpenSearch, Kendra, and other AWS AI services.
Key Features
AWS-native embedding model
Optimized for Amazon OpenSearch integration
Strong semantic similarity performance
Configurable dimensionality
Support for document and query embeddings
Ideal Use Cases
AWS-native search and retrieval applications
Amazon Bedrock RAG pipelines
Enterprise search within AWS ecosystem
Document similarity and deduplication
Technical Specifications
| Dimensions | 1024 (configurable) |
| Modality | Text → Embedding |
| Provider | Amazon |
| Category | Embedding |
| Platform | Amazon Bedrock / Vercel |
API Usage
1 curl -X POST https://api.vincony.com/v1/chat/completions \ 2 -H "Authorization: Bearer YOUR_API_KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "amazon/titan-embed-text-v2", 6 "messages": [ 7 { "role": "user", "content": "Hello, Titan Embed Text V2!" } 8 ] 9 }'
Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.
Compare with Another Model
Frequently Asked Questions
Try Titan Embed Text V2 now
Start using Titan Embed Text V2 instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from Amazon
Use ← → to navigate between models · Esc to go back