llmcloud.ai
zero margin · vetted providers · an opinion per workload

One AI Gateway
for all your LLMs

The gateway is free forever. You pay the provider's list price, itemised on every receipt — we take nothing. Every provider is graded before it serves you.

$0 gateway fee · no prepaid credits · works with the OpenAI SDK

0%
routing fee
312
models
28
providers
99.9999%
combined uptime
142ms
p50 latency

Routing, extended

Every request, routed with intent.

OpenRouter's one-endpoint promise, extended with the primitives agentic developers actually reach for.

auto:*

Smart routing

auto:quality, auto:cost, auto:speed, auto:reasoning — a contextual bandit picks the upstream that wins on the axis you care about, per request.

Inside the router

cache-hit routing

Semantic caching

Near-duplicate prompts get served from a shared cache instead of a model. Same answer, ~zero cost, sub-100ms TTFT.

How caching routes

thinking, unified

Reasoning trace

One field for step-by-step traces across o-series, Claude thinking, DeepSeek-R, and Qwen — no vendor-specific shim.

auto:reasoning

grounded

Web-grounded answers

Pass tools: ['web_search'] and the router picks the cheapest search-capable model. Citations returned in a standard shape.

Docs & schema

one connector

MCP endpoint

Add mcp.llmcloud.ai to Claude Code, Cursor, or Windsurf and every model becomes a tool call — routed by the same policies.

Install snippets

multimodal in

Vision, audio, PDF

Send images, audio, and documents to any capable model through the same auto: policy. Router filters on modality automatically.

Browse multimodal
Also supportedImage generationFunction callingStructured outputsSSE streamingJSON modeBYO keys

Opinionated defaults

We'll tell you which model to use

See all 8 workloads →
WorkloadDefault pickDirective
Coding agentanthropic/claude-sonnet-4.5auto:coding
Function calling & agentsopenai/gpt-5auto:tools
Long-context retrievalgoogle/gemini-3.1-proauto:long-context
Batch classification & extractionopenai/gpt-5.5-miniauto:cost

Migrate

From OpenRouter in two lines.

Same OpenAI-compatible protocol. Same provider/model IDs. Keep every tool call, streaming behavior and JSON-mode contract — gain routing policies, caching, guardrails and per-key IAM.

diff — client init
  const client = new OpenAI({
-   baseURL: "https://openrouter.ai/api/v1",
-   apiKey: process.env.OPENROUTER_API_KEY,
+   baseURL: "https://api.llmcloud.ai/v1",
+   apiKey: process.env.LLMCLOUD_API_KEY,
  });

Trending

Top models this week

Full leaderboard →
01
claude-opus-4.5
Anthropic
94.2q
$15.00/M
02
gpt-5.5
OpenAI
93.8q
$12.50/M
03
claude-opus-4.1
Anthropic
93.1q
$15.00/M
04
gpt-5
OpenAI
92.4q
$10.00/M
05
gemini-3.1-pro
Google
92.1q
$7.00/M
06
gpt-5-codex
OpenAI
91.2q
$4.50/M
07
claude-sonnet-4.5
Anthropic
90.8q
$3.00/M
08
grok-5
xAI
90.6q
$6.00/M

Get started

Live in three steps

Full quickstart →
01

Sign up

Create an account with Google, GitHub, or email. Spin up an org for your team any time.

02

Add a payment method

No prepaid credits, no minimums. You are billed the provider's list price in arrears — the gateway itself is $0.

03

Get your API key

Drop the key into the OpenAI SDK, point base_url at api.llmcloud.ai, and start streaming.

Point your OpenAI SDK at us.

Pay the provider, not us. Swap one URL and get every frontier and open model at list price.