LEANROUTE

AI Gateway · Native MCP

One AI Gateway for Models and Tools.

14 LLM Providers. Native MCP. Cut down your LLM bill by half.

One OpenAI-compatible endpoint. Bring your own keys or top up credits.

Native MCP forwardingPer-org MCP allowlistsZero per-request markup
Get an API key →Try the sandbox — no signup

OpenAI-compatible. Point your SDK at api.leanroute.dev/v1 and you're running.

60 seconds to first requestsign up → mint key → change one env var → done
Your appOpenAI SDKLEANROUTEsmart routingauto-failovercacheguardrailsspend capsMCP passthroughapi.leanroute.dev/v1Singapore-hostedLLM PROVIDERSOpenAIAnthropicGoogleDeepSeek+ 10 more (xAI, Groq, Qwen…)MCP SERVERSyour Calendaryour Docsany MCP URL

The chat bubble in the corner is built on Leanroute + RAG. Read the writeup →

Platform

Five pillars. One control plane.

Everything below is shipping in production today.

LLM routing

14 providers, one OpenAI-compatible endpoint. Cheap-fast tier, smart routing, failover on upstream 5xx.

Model catalog

Prompt & semantic cache

Semantic cache serves near-duplicate prompts at $0, org-isolated. Exact matches free too.

How caching works

Guardrails

Regex block, regex redact, and OpenAI moderation. Seven-rule starter library ships in.

Rule library

MCP + A2A

mcp_servers forwarded to Anthropic natively. Per-org allowlists today; chain-aware policy on the roadmap.

MCP docs

Spend control

Hard daily and monthly caps per org and per key. Rate limits enforced at the edge.

Pricing

Dashboard

Every dollar, every provider, every request.

Cost over time. Cache-hit rate. Per-provider breakdown. Per-request logs with model, latency, and status. Included on every plan.

leanroute.dev/dashboard/usage
Leanroute usage dashboard — cost-over-time bar chart and per-provider breakdown showing Anthropic, xAI, Sarvam, Groq, DeepSeek, Google, OpenAI, Qwen, Kimi, and Krutrim with real spend data over 12 weeks

Real screenshot from a production account. See the full walkthrough at /docs.

Providers

14 providers, one endpoint, your existing SDK.

Every provider below is reachable through api.leanroute.dev/v1. Change the base URL, keep everything else. Full model catalog at /docs/models.

OpenAI
Anthropic
Google
xAI
DeepSeek
Qwen
GLM
Doubao
Kimi
Sarvam
Krutrim
Meta
Groq
AWS Bedrock

One integration. Every provider.

Same providers. Less code.

BEFOREWITH LEANROUTEYour app5 SDKs, 5 auth flowsopenai-sdkanthropic-sdkgoogle-genaideepseek-apidashscopeOpenAIAnthropicGoogleDeepSeekQwen5 wire formats · 5 auth flows · 5 dashboardsEvery provider swap ships behind a code change.Your appopenai-sdk onlyapi.leanroute.dev/v1LEANROUTEOpenAIAnthropicGoogleDeepSeekQwen1 wire format · 1 auth flow · 1 dashboardSwap providers with a config change, not a code change.

Before — per-provider code

import openai
import anthropic
from google import genai
# ... 3 more imports

r = openai.chat.completions.create(...)
r = anthropic.messages.create(...)
r = genai.generate_content(...)
# each provider: different shape,
# different auth, different retry logic

With Leanroute — one SDK

from openai import OpenAI

client = OpenAI(
  base_url="https://api.leanroute.dev/v1",
  api_key=LEANROUTE_KEY,
)

r = client.chat.completions.create(
  model="anthropic/claude-sonnet-5",
  # or deepseek/deepseek-v4-flash, etc.
  messages=[...],
)

Pricing

Flat monthly BYOK or pay-as-you-go credits.

Zero per-request markup on inference either way.

Starter

$15/mo

1M requests · 30 RPM

Pro

Recommended
$25/mo

5M requests + $3/1M overage · 150 RPM

14 days free · cancel anytime

Credits

5% platform fee

Applied at deposit only · $0 per request · $50 min top-up

Larger team?

Let's talk

Design-partner terms — email us

At $1,000/mo of provider spend:Leanroute Pro $1,025vs OpenRouter $1,050vs Portkey Prod $1,049+

Zero per-request markup means the savings widen as your bill grows. Run your own numbers →

Self-hosted / private-deploy? Not shipped yet — we're gauging demand.Join early-access list →
Read the full FAQ →See how we compare →