AWS Bedrock + SemanticGuard

Reduce AWS Bedrock costs
by up to 70%.

Add intelligent caching to your Bedrock models. Supports Llama, Titan, Cohere, and Claude. Your prompts stay in AWS. One line of code.

AWS Bedrock with SemanticGuard
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://semanticguard.dev/api/proxy/v1",
apiKey: "not-used",
defaultHeaders: {
"x-sg-api-key": "sg-your-key-here",
"x-sg-aws-access-key": process.env.AWS_ACCESS_KEY_ID,
"x-sg-aws-secret-key": process.env.AWS_SECRET_ACCESS_KEY,
"x-sg-aws-region": "us-east-1",
},
});
const response = await client.chat.completions.create({
model: "meta.llama3-70b-instruct-v1:0",
messages: [{ role: "user", content: "Summarize this report..." }],
});

Supported Bedrock Models

Meta Llama 3 (8B, 70B)Amazon Titan TextCohere Command R/R+Anthropic Claude (Bedrock-hosted)AI21 Jurassic
$

Keep your AWS committed spend

Requests route through your Bedrock deployment. SemanticGuard caches responses so identical or similar prompts never hit the API twice.

Measured cache correctness

Intelligent caching understands when two prompts mean the same thing. 100% measured correctness on our public benchmark — see /benchmark. Cache hits return in under 50ms.

Data stays with AWS

Your prompts never leave your contracted provider. Entity extraction uses your Bedrock models. Full data residency compliance.

How It Works with Bedrock

1

Point to SemanticGuard

Use the OpenAI SDK with SemanticGuard's base URL and your AWS credentials. No Bedrock SDK required.

2

Requests flow through Bedrock

SemanticGuard signs requests with SigV4 and forwards them to your Bedrock endpoint. Your data stays in AWS.

3

Save on every duplicate

Similar prompts return cached responses in under 50ms. Your Bedrock spend drops without sacrificing response quality — 100% measured correctness on our public benchmark.

Built for production AWS workloads

OpenAI-compatible API

Use the OpenAI SDK to call Bedrock models through SemanticGuard. No Bedrock SDK needed.

Same-vendor routing

All auxiliary calls use your Bedrock models. No data shared with other providers.

Full visibility

Real-time cost dashboard shows spend by model, project, and request. See exactly what you save.

Edge-native signing

Lightweight AWS SigV4 signing runs on the edge. No AWS SDK dependency, no cold starts.

Start saving on AWS Bedrock today

Free tier includes 10K requests/mo with Shadow Mode. See your potential savings before enabling caching.