Production LLM API platform

One gateway for every model you ship.

Aggregate provider keys, route across pools, and meter usage — behind a single OpenAI- and Anthropic-compatible API. Swap the base URL. Keep your stack.

Start free View examples

API key for every model

One lm0_ secret across the catalog

API surfaces unified

Chat, Messages, and Responses

SDK rewrites required

Swap base URL. Keep your code.

Works with the tools you already use

Drop-in surfaces for the clients and frameworks you already ship with.

OpenAI SDK

chat/completions · responses

Anthropic SDK

messages API

LiteLLM

drop-in proxy

LangChain

base URL swap

HTTP

cURL / HTTP

any client

Custom agents

Bearer lm0_…

Features

Everything between your app and the models

LM0 is the control plane for LLM traffic — routing, metering, keys, and status — so you never rebuild gateway plumbing again.

SDK-ready

Drop-in API compatibility

OpenAI chat completions, Anthropic messages, and Responses — one gateway, zero rewrites. Point your SDK at LM0 and keep shipping.

Multi-pool

Unified model catalog

Route across provider pools with automatic fallbacks. One key unlocks every model you ship — flash, frontier, and everything between.

Metered

Usage & credits built-in

Per-request token accounting, model breakdowns, and credit balances you can actually trust. No surprise bills, no opaque metering.

Resilient routing

Automatic failover across pools keeps completions flowing when a provider hiccups. Your users never see the seams.

Security

Keys & access control

Mint scoped API keys, rotate secrets, and manage teams from a clean console. Built for solo builders and production teams alike.

Observability

Live model status

See success rates and health across the catalog in real time. Know which models are green before you depend on them.

The product

A gateway that feels like infrastructure

Not another chat UI. LM0 is the API layer between your product and every model pool — with credits, keys, and observability baked in.

One key. Every pool.

Stop juggling provider dashboards. LM0 aggregates keys and routes traffic across model pools so you can focus on product, not plumbing.

Single lm0_ secret
OpenAI + Anthropic surfaces
Pool-level fallbacks

Metering you can audit

Every request is accounted for — tokens in, tokens out, model, and cost. Credits and packages stay transparent in the console.

Per-request ledgers
Model-level breakdowns
Package + top-up balances

Built for production

Status monitoring, support channels, and a reseller program when you need to scale distribution. Infrastructure that grows with you.

Live success rates
Support tickets
Reseller tooling

Request path

Your app → LM0 gateway → model pools → metered response

Your app / agent

LM0 Gateway

Model pools

Usage ledger

Quick start

Ship in minutes

Three steps from zero to production completions.

01
Create an account

Sign up in under a minute and receive free welcome credits to explore the catalog.
02
Mint an API key

Copy your base URL and secret once. Same key works for chat, messages, and responses.
03
Call any model

Use model IDs from the catalog in your existing OpenAI or Anthropic SDK. Swap base URL, keep your code.

Compatible with the OpenAI SDK, Anthropic SDK, LiteLLM, LangChain, and any HTTP client. Swap the base URL, keep your code. Welcome credits included so you can try models before you commit.

Free welcome credits on signup
Console for keys, usage & billing
Live model status dashboard

Create free account Sign in

Code

Same call, your language

Point your existing client at api.17.wtf and authenticate with your LM0 key.

from openai import OpenAI

client = OpenAI(
  base_url="https://api.17.wtf/v1",
  api_key="lm0_…"
)

r = client.chat.completions.create(
  model="posiden/deepseek-v4-flash",
  messages=[{"role": "user", "content": "Hello"}]
)
print(r.choices[0].message.content)

Ready to route smarter?

Create an account, mint a key, and call any model in the catalog — today.

Get started free Explore features