Now with Built-in AI LLM Proxy

AI-Powered
Cloud Networking

Replace expensive managed networking services with a single intelligent gateway. Built-in LLM proxy with response caching. 95% cost savings. Available on AWS, coming soon to GCP and Azure.

View Pricing Interactive Calculator
95%
Cost Reduction
$0
Per-GB Fees
10min
Deploy Time
3
Providers (1 SDK)
Cost Comparison
Stop Paying Per-GB
Cloud providers charge for every byte. Here's what 100 TB/month costs with managed services vs Camphor AI Gateway.

Cloud Managed Services at 100 TB/mo

NAT Gateway (AWS / GCP / Azure)$4,533/mo
Network Firewall (AWS / GCP / Azure)$6,788/mo
Load Balancer (NLB / GLB / ALB)$616/mo
Transit / Peering (TGW / Interconnect)$2,000/mo
LLM API GatewayBuild your own
Total$13,937/mo
→

Camphor AI Gateway on c8in.xlarge

sNAT + dNAT$0/GB
Suricata IDS/IPS$0/GB
IPVS L4 + TLS$0/GB
VPC / VNet Peering Mesh$0/GB
AI LLM Proxy + CacheIncluded
Total (EC2 + Camphor)$397/mo
97% savings
AI LLM Gateway
One API for Every LLM Provider
Use the OpenAI SDK for Claude, GPT, and Bedrock. Response caching saves 30-70% on API costs. Zero code changes.
# One SDK for everything -- just change the model name
from openai import OpenAI

client = OpenAI(base_url="http://ai.gw.internal:8080/v1")

# OpenAI
client.chat.completions.create(model="gpt-4o", ...)

# Anthropic Claude (auto-translated)
client.chat.completions.create(model="claude-sonnet-4", ...)

# AWS Bedrock (SigV4 auto-signed)
client.chat.completions.create(model="bedrock/anthropic.claude-3-haiku", ...)
3
LLM Providers
50-70%
Cache Hit Rate
$0
Extra Cost
0ms
Cached Response
Features
Everything You Need, One Appliance
25+ shipped features across networking, security, and AI. All managed from a single dashboard.
⇄

sNAT + dNAT

Source NAT for internet access, port forwarding for inbound. Zero per-GB fees.

Gateway
⚖

NLB Replacement (IPVS L4)

Sync AWS NLB config to IPVS kernel rules. TLS termination via HAProxy.

Gateway
✨

AI LLM Proxy

Route to OpenAI, Anthropic, Bedrock via single SDK. Response caching, token counting, cost attribution.

AI
♥

High Availability

Per-AZ ASG with warm pool for sub-10s recovery. EIP failover with per-AZ DNS.

Gateway
↕

Vertical + Horizontal Scaling

Auto instance type change with zero downtime. GWLB for multi-instance linear scaling.

Gateway
🛡

Suricata IDS/IPS

Sync rules from AWS Network Firewall -- no endpoints needed ($0/month). ET Open 30K+ threat rules.

Security
🌐

L7 HTTP Proxy

Distributed Squid proxy with per-AZ DNS, caching, NCSA auth, and domain filtering. $0/GB.

Gateway
🔒

AI Prompt Audit

Log every LLM API call with model, tokens, cost, and source IP. Compliance-ready JSON format.

AI
📌

VPC Peering Mesh

Transit Manager auto-discovers VPCs across accounts and regions. Auto-creates full-mesh peering with route propagation. $0/GB data-plane cost.

Enterprise
🔗

Hub-Spoke Agent (ECMP + VPN)

GRE tunnels from spoke VPCs to hub with ECMP load balancing across gateway instances. WireGuard VPN for remote clients. Centralized NAT and IDS/IPS for all spokes.

Enterprise
⎈

Multi-Account Kubernetes

K8s control plane in your hub VPC. Worker nodes span 3 accounts, 3 regions, 8 VPCs with Calico IPIP. Camphor Karpenter provider for cross-account node provisioning.

Enterprise
🤖

AI Ops Assistant (Beta)

Chat with your gateway in natural language. Powered by Amazon Bedrock. Query topology, troubleshoot connectivity, and understand traffic patterns via real-time SSE streaming.

AI
Deployment
Deploy in 10 Minutes
No agents, no sidecars, no Kubernetes required. One-click deployment on AWS today.
1

Subscribe on Marketplace

Subscribe to Camphor AI Gateway on AWS Marketplace. The machine image is automatically configured for your cloud environment.

2

Launch Your Stack

Choose your VPC (new or existing), instance type, and availability zones. Infrastructure-as-code creates everything automatically.

3

Route Traffic

Point your private subnets to the Camphor gateway. All traffic flows through Camphor for NAT, firewall, and AI proxy.

AWS — Available Now GCP — Coming Soon Azure — Coming Soon
Private Subnet App Servers AI Workloads Databases Camphor AI Gateway sNAT/dNAT IDS/IPS IPVS L4 HTTP Proxy AI LLM Proxy + Cache Dashboard + API + Terraform $0/GB Internet Egress via EIP LLM APIs OpenAI / Claude Bedrock / Gemini
Pricing
Simple Hourly Pricing, No Per-GB Fees
Pay a flat software fee per instance-hour. EC2 cost is separate (your AWS bill). Spot discounts apply to EC2 only.

Gateway

NAT + NLB + AI LLM Proxy
1.0x premium
  • sNAT + dNAT (port forwarding)
  • NLB replacement (IPVS L4)
  • L7 HTTP Proxy (Squid) with caching
  • EIP failover + TLS termination
  • Per-AZ ASG + vertical/horizontal scaling
  • AI LLM Proxy with response caching

Security Gateway

+ Firewall + AI Security
2.0x premium
  • Everything in Gateway
  • Suricata IDS/IPS + nftables
  • Domain filtering + ET Open threats
  • TLS inspection (SSL bump)
  • AI prompt audit logging

Enterprise Gateway

+ Transit + AI Semantic Cache
4.0x premium
  • Everything in Security
  • Cross-account transit manager
  • VPC peering mesh (auto routes)
  • Hub-spoke agent (ECMP + WireGuard VPN)
  • Multi-account Kubernetes (17 nodes, 3 regions)
  • AI semantic cache (50-70% hit rate)
  • $100/mo management subscription
Open Interactive Pricing Calculator
Use Cases
Built For

Startups

Replace $500+/month in AWS networking costs with a $30/month t4g.medium. AI proxy included free. Ship faster, spend less.

AI Companies

Route all LLM API calls through a single gateway with caching. Cut API costs 30-70%. Audit every prompt for compliance.

Enterprise

Full-mesh VPC peering across 100+ accounts. IDS/IPS with zero per-GB fees. AI semantic caching at scale.

FAQ
Common Questions

Appliance or proxy?

A full EC2 appliance inside your VPC. Traffic never leaves your network -- Camphor sits in the data path like a NAT gateway, but with firewall, load balancing, and AI proxy built in. No agents, no sidecars, no code changes.

What if the gateway fails?

Each AZ has its own Auto Scaling Group with a warm pool for sub-10s recovery. EIPs fail over automatically. Multi-instance mode adds GWLB health-checked distribution across gateways.

vs. AWS Transit Gateway?

Transit Gateway charges $0.02/GB for every byte. Camphor uses free VPC peering with auto-created routes, full-mesh topology, and cross-account management -- all at $0/GB.

View all FAQs →
Built on proven open-source
nftables IPVS Suricata HAProxy Squid WireGuard Terraform Kubernetes Calico CNI

Ready to Save 95%?

Deploy Camphor AI Gateway in your cloud in under 10 minutes. No agents, no sidecars, no commitments.

View Pricing Interactive Calculator