No VC money burned in the making of this product

25+ free models. Smart routing. 4% markup.

The indie LLM router that tries free models first. OpenAI-compatible API, waterfall routing from free to cheap to premium. Built by one person + Claude, not 20 engineers in SF.

25+
Free Models
$0
For Simple Queries
4%
Markup (vs 5.5%)
1M
Token Context FREE

How waterfall routing works

Your request cascades down from free to paid until it gets a great answer. Most of the time, free is all you need.

1. Send a request

Use our OpenAI-compatible API. Drop-in replacement -- change one line of code and you are done.

2. Smart routing

We try free models first (DeepSeek, Gemini, Llama), then cheap ones, then premium. Only escalate when needed.

3. Save money

Most queries resolve on free models. You only pay when you actually need a premium model. Simple as that.

Featured models

From free reasoning models to flagship paid ones. Pick what fits your budget and task.

Gemini 2.5 Pro
Google

Google's most capable model with 1M context. Free experimental access through Waterfall.

Free1M context
ChatVisionReasoningCodeTool Use
DeepSeek R1
DeepSeek

State-of-the-art reasoning model competitive with o1. Completely free through Waterfall.

Free164K context
ChatReasoningCode
New
Llama 4 Maverick
Meta

Latest Llama with 1M context and excellent tool calling. Free on Waterfall.

Free1M context
ChatTool UseCode
DeepSeek V3 Chat
DeepSeek

Excellent all-around chat model. 128K context. Free on Waterfall.

Free128K context
ChatTool UseCode
Llama 4 Scout
Meta

Llama 4 Scout on Groq. Ultra-fast inference at $0.11/M input tokens.

$0.11/$0.34 per M512K context
ChatTool UseCode
New
Claude Sonnet 4
Anthropic

Anthropic's latest balanced model. Excellent coding and reasoning.

$3.00/$15.00 per M200K context
ChatVisionTool UseCodeReasoning

Waterfall vs OpenRouter

They raised $40M to route to expensive models. We route to free ones first. Different philosophy.

OpenRouterWaterfall
Funding$40M raised, $500M valuationBootstrapped, profitable
Team20+ engineers in SFJulie + Claude
Fees5.5% credit purchase fee4% transparent markup
RoutingRoutes to paid models firstRoutes to FREE models first
Free modelsSome, as afterthought25+ free models, first-class
Philosophy"Which expensive model is best?""Can a free model handle this?"

Ready to save on AI?

Drop-in OpenAI-compatible API. Change one line of code. Start with free models, scale to premium when you need to.

$7/month VPS. Not $40M in funding. We pass the savings to you.