Looking Beyond AWS Bedrock?

Bedrock gives you the models AWS hosts. LLM Gateway gives you multiple labs and clouds — including Bedrock itself — behind one open-source, OpenAI-compatible API with automatic routing and failover.

Cloud-NeutralOpen-Source CoreCross-Cloud FailoverBedrock Built In
Start for Free
View Documentation
Compare platforms

Keep Bedrock and add cross-provider routing

Compare LLM Gateway and Amazon Bedrock features side by side

Why choose LLM Gateway?

No cloud lock-in — Bedrock is one of the supported providers behind a single OpenAI-compatible API
Cross-cloud failover — retryable failures can fall back to an eligible alternative provider when routing settings allow it
Open-source core — self-host under AGPLv3; enterprise features have separate terms
Keep your Bedrock setup — bring your AWS credentials and route through Bedrock with 0% markup

LLM Gateway

OPEN-SOURCE & CLOUD-NEUTRAL

From $0

Free core; hosting costs separate

Bedrock

AWS MANAGED AI SERVICE

Usage-based

Requires an AWS account

Cloud-neutral

Choose from supported providers across clouds

AWS only

Open source & self-hostable

Run the core on your infrastructure; Enterprise has separate terms

AGPLv3

OpenAI-compatible API

Common request formats; features depend on the model

Chat Completions / Responses; model-dependent

Setup required

What you need before your first request

Sign up, copy a key
AWS account, permissions, eligible model

Providers behind one API

Clouds, labs, and fast independent hosts

See live provider catalog
AWS-hosted catalog

Frontier model coverage

Check live catalogs for the models you need

Cross-provider catalog
See Bedrock model catalog

Fast inference hosts

Choose independent inference hosts

Image & video generation

Generative media through the same API

Across providers
Supported media models

Automatic provider routing

Routes on live uptime, throughput, price, and latency

Cross-region and intelligent prompt routing

Failover across providers

Retry within the configured model and provider pool

Response caching

Built-in caching for repeated requests

Redis, 10s–1yr TTL
Prompt caching (select models)

Route to AWS Bedrock

Keep Bedrock in the mix as one provider among many

Built-in provider
—

Bring your own keys

Use your own provider credentials

0% markup
N/A (AWS billing)

Transparent platform fee

Predictable, easy-to-reason-about pricing

5% or 0% (BYOK)
AWS model, region and service-tier rates

Real-time cost analytics

Per-request cost, latency, and usage in one dashboard

CloudWatch / Cost Explorer

Content guardrails

Content checks; coverage and pricing vary by product

Enterprise

Already on Bedrock? Keep it — and stop depending on it.

AWS Bedrock is a built-in LLM Gateway provider. Bring your AWS credentials and your Bedrock traffic keeps flowing with 0% markup — with configurable provider fallback, response caching, and cost analytics. Content guardrails require Enterprise. Check our live catalog for supported routes outside Bedrock.

Start Free with LLM GatewayView Pricing Details

No credit card required • Self-host option available • Enterprise support available

FAQ

LLM Gateway vs AWS Bedrock

Common questions about using LLM Gateway alongside or instead of Amazon Bedrock.

Can't find an answer? Contact us

Bedrock is a strong choice when model access, IAM, private networking and billing should stay within AWS. It also offers managed agents, knowledge bases and guardrails. LLM Gateway is useful when you need routing across independent providers as well as supported Bedrock models.