Blog
Notes from the gateway
Product updates, routing math, and the occasional deep dive into what an LLM gateway actually does under the hood. RSS.
- 8 min read
What is an Agent-Native AI Gateway? (And Why Legacy LLM Proxies Break)
AI gateways built for 2024 chat apps fail when faced with autonomous coding agents, multi-agent workflows, and MCP tools. Here is the architectural definition of an agent-native AI gateway.
AI GatewayAutonomous AgentsMCPModel Context ProtocolLLMDevOpsFinOps - 8 min read
OpenRouter vs LiteLLM (2026): Hosted Marketplace or Self-Hosted Proxy?
OpenRouter vs LiteLLM: fees, BYOK, self-hosting effort, security and model coverage compared, with clear picks for each, plus a managed BYOK middle option.
OpenRouterLiteLLMOpenRouter vs LiteLLMAI GatewayLLM GatewayBYOKComparison - 4 min read
Singapore-Hosted AI Gateway: Running Production LLMs and Agents Under PDPA, DPDP, and APPI
Why engineering teams in Singapore, India, and APAC use a Singapore-hosted AI gateway with no-persistence caching, client-side encrypted BYOK, and first-class APAC models instead of US-only routers.
SingaporePDPAData ResidencyComplianceAI GatewayAPACBYOK - 5 min read
Gateway-Run MCP Loop vs. Passthrough: Why Agent Tool Calling Belongs at the AI Gateway
Most AI gateways either ignore Model Context Protocol (MCP) or forward mcp_servers only to Anthropic. Here is how running the MCP agent loop at the gateway makes tools work on GPT, Gemini, DeepSeek, and Groq with one audit trail.
MCPModel Context ProtocolAI GatewayLLM GatewayAgent ArchitectureTool Calling - 4 min read
Leanroute for n8n: a community node for AI Agent workflows
Install n8n-nodes-leanroute to use 100+ models from 14 providers in n8n AI Agents, with spend caps, caching and failover for workflows that run unattended. Setup in five minutes, plus what works and what doesn't yet.
n8nAI Agentworkflow automationLLM Gateway - 5 min read
Spend caps and rate limits for LLM APIs, per team and per key
How to stop a runaway agent or a leaked key from burning your LLM budget: daily and monthly spend caps, per-key limits, requests and tokens per minute, 80% alerts, and how to handle the errors in your code.
LLM GatewayFinOpsspend capsrate limiting - 5 min read
LLM routing with Leanroute: tiers, policies and failover
How Leanroute decides which model and provider serve a request: quality tiers, cheaper-model swaps, provider allow and block lists, failover, and the response headers that let you audit every decision.
LLM GatewayLLM routingfailovercost optimization - 6 min read
LLM guardrails at the gateway: PII, secrets and prompt injection
How to stop personal data and credentials from reaching an LLM provider: redact or block at the gateway, try rules safely in preview mode, add your own patterns, and know where pattern-based guardrails stop.
LLM GatewayguardrailsPIIsecuritycompliance - 6 min read
Five questions to ask before you pick an AI gateway
Routing, price accuracy, spend caps, guardrails and semantic caching. The five questions a gateway evaluation actually turns on, what the honest answers sound like, and the one nobody is asking yet.
LLM GatewayAI GatewayFinOpsevaluationguardrails - 5 min read
MCP tool calling on any model, not just Claude
We replaced our MCP forwarder with a gateway-run agent loop, so the same MCP tools work on GPT, Gemini, DeepSeek and Groq. What it took, and three bugs it exposed.
MCPModel Context ProtocolLLM Gatewaytool callingproduct - 6 min read
Announcing opa-sidecar-a2a: A Reference Implementation for Chain-Aware Agent Authorization
Agent-to-agent traffic is going into production faster than the authorization models are catching up. We built and open-sourced a reference implementation that shows what chain-aware authorization looks like, using Open Policy Agent as the engine. MIT licensed, Go, single binary.
A2AAgent AuthorizationOPAOpen Policy AgentChain-aware AuthorizationOpen SourceMCP - 11 min read
Best Portkey Alternatives in 2026: 6 AI Gateways Compared
Leaving Portkey after the Palo Alto deal? 6 alternatives compared on pricing, self-hosting and MCP: Leanroute, LiteLLM, Bifrost, Kong, Helicone, OpenRouter.
PortkeyPortkey alternativeAI GatewayLLM GatewayPalo Alto NetworksBYOKComparison - 9 min read
Kong AI Gateway Alternative (2026): When a Managed BYOK Gateway Wins
Kong AI Gateway is the enterprise procurement-safe pick, with $30-50K+ annual contracts and a real setup surface. Honest comparison of alternatives (Leanroute, LiteLLM, Bifrost, Portkey) and when Kong is genuinely the right call.
Kong AI GatewayKong alternativeAI GatewayLLM GatewayEnterpriseBYOKComparison - 11 min read
Bifrost Alternatives 2026: Bifrost vs OpenRouter vs Managed
Bifrost (self-hosted Go) vs OpenRouter vs Leanroute: hosting, gateway overhead, BYOK pricing and MCP tool calling compared, plus when to stay on Bifrost.
BifrostBifrost alternativeAI GatewayLLM GatewayMaxim AILiteLLMBYOKComparison - 8 min read
AWS Bedrock via Leanroute: BYOK, Unified Logs, and Multi-Provider Routing
AWS Bedrock is a great managed model service. It is not a gateway. Here is how teams use Bedrock through Leanroute to get unified BYOK across Bedrock plus 13 non-AWS providers, gateway-edge spend caps, and OpenAI-compatible wire format on top of Bedrock's Anthropic and Meta models.
AWS BedrockBedrockAI GatewayLLM GatewayBYOKIAMMulti-cloud - 9 min read
FinOps for LLM Spend: Three Reasons Your Bill Changed
When your LLM bill moves, three separate things could have caused it. Your usage changed, your pricing changed, or the way your app talks to the model changed. Mixing them up is how teams end up thanking the wrong lever. A simple framework for pulling them apart.
FinOpsLLM CostAI EconomicsCost AttributionAI GatewayLLM GatewayBYOK - 6 min read
OpenRouter Alternative: When a BYOK Gateway Actually Beats OpenRouter (2026)
When does a flat $15/mo BYOK gateway beat OpenRouter? An honest look at fees, the $25k free BYOK allowance, MCP tools on any model, guardrails and APAC models.
OpenRouterOpenRouter alternativeAI GatewayLLM GatewayBYOKCost OptimizationLLM Routing - 9 min read
LiteLLM Alternatives 2026: 5 Gateways Compared (Post-CVE-2026-35029)
Looking for a LiteLLM alternative? Compare Leanroute, Portkey, OpenRouter, Kong & Helicone with a decision tree for managed BYOK vs self-hosted Python.
LiteLLMLiteLLM alternativeAI GatewayLLM GatewayPortkeyKong AI GatewayHeliconeOpenRouterComparison - 8 min read
Self-Hosting an LLM Gateway: When It's Right, When It's Not
LLM middleware holds every provider key in your stack, sees every prompt, and often has admin access to spend caps. Self-hosting it means owning the full operational surface. A recent LiteLLM CVE is a reminder to make that choice deliberately, not by default.
AI GatewayLiteLLMSelf-HostingManaged ServicesLLM InfrastructureSecurityDevOps - 10 min read
Chain-aware Authorization: OPA + MCP for the A2A Auth Problem
AI agents are nothing but APIs on cron with autonomy and reasoning. Everything we learned about API authorization still applies. Here is the pattern I think should become standard, and the reason it works.
AI AgentsAuthorizationMCPOPAA2AAI InfrastructureLLM - 14 min read
Cut Claude Code Bills 60% by Routing to DeepSeek and Groq
Claude Code defaults to Sonnet. Sonnet is great. Sonnet is also expensive. Here is a practical walkthrough for routing your Claude Code sessions across 14 providers, keeping the same tools and prompts, and cutting your bill by more than half.
Claude CodeLLM RoutingAI GatewayCost OptimizationDeepSeekGroqMCP - 5 min read
Migrating from OpenRouter to Leanroute
Already using OpenRouter? Learn how to migrate to Leanroute while keeping your OpenAI-compatible integration and adding MCP tools on any model.
OpenRouterAI GatewayLLM GatewayMCPAI InfrastructureLLM Routing - 3 min read
Deepseek Price Hike, Routing Arbitrage Saves Cost
DeepSeek Raised Prices and Added Peak Hours. Here’s How Routing Arbitrage Keeps Your LLM Bill Under Control
AI GatewayLLM GatewayMCPAI InfrastructureLLM Routing - 3 min read
Stop Building Your Own LLM Router
Model routing looks simple until you have to maintain it. Here's why most AI teams should use routing infrastructure instead of building their own.
AI GatewayLLM RoutingAI InfrastructureLLMDeveloper Tools - 5 min read
Why Every AI Gateway Will Need to Speak MCP
AI Gateways solved model fragmentation. The next challenge is tool fragmentation. Here's why the future of AI infrastructure is one gateway for models and tools.
AI GatewayMCPModel Context ProtocolAI InfrastructureProduction AI - 12 min read
What Is an AI Gateway? The Complete Guide for Production AI Applications (2026)
Learn what an AI Gateway is, why production AI applications need one, and how model routing, failover, and MCP are changing AI infrastructure.
AI GatewayLLM GatewayAI InfrastructureModel RoutingMCP