I built a $2/month Claude API proxy — here's the curl command
<h1> I built a $2/month Claude API proxy — here's the curl command </h1> <p>I got tired of paying $20/month for Claude Pro just to use Claude Code.</p> <p>So I built a flat-rate Claude API proxy. Here's everything you need to use it.</p> <h2> The one-line setup </h2> <div class="highlight js-code-highlight"> <pre class="highlight shell"><code><span class="nb">export </span><span class="nv">ANTHROPIC_BASE_URL</span><span class="o">=</span>https://api.simplylouie.com <span class="nb">export </span><span class="nv">ANTHROPIC_API_KEY</span><span class="o">=</span>your_key_here </code></pre> </div> <p>That's it. Every tool that uses <code>ANTHROPIC_BASE_URL</code> now routes through the proxy.</p> <h2> Test it with curl </h2> <div class="highlight js-code-highlight"> <pre class="highlight shell
I built a $2/month Claude API proxy — here's the curl command
I got tired of paying $20/month for Claude Pro just to use Claude Code.
So I built a flat-rate Claude API proxy. Here's everything you need to use it.
The one-line setup
export ANTHROPIC_BASE_URL=https://api.simplylouie.com export ANTHROPIC_API_KEY=your_key_hereexport ANTHROPIC_BASE_URL=https://api.simplylouie.com export ANTHROPIC_API_KEY=your_key_hereEnter fullscreen mode
Exit fullscreen mode
That's it. Every tool that uses ANTHROPIC_BASE_URL now routes through the proxy.
Test it with curl
curl https://api.simplylouie.com/v1/messages \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-opus-4-5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}] }'curl https://api.simplylouie.com/v1/messages \ -H "x-api-key: $ANTHROPIC_API_KEY" \ -H "anthropic-version: 2023-06-01" \ -H "content-type: application/json" \ -d '{ "model": "claude-opus-4-5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}] }'Enter fullscreen mode
Exit fullscreen mode
You get a real Anthropic-format response. Your existing tools don't know the difference.
Use it with Claude Code
# In your shell profile export ANTHROPIC_BASE_URL=https://api.simplylouie.com export ANTHROPIC_API_KEY=sl_your_key_here# In your shell profile export ANTHROPIC_BASE_URL=https://api.simplylouie.com export ANTHROPIC_API_KEY=sl_your_key_hereNow run Claude Code normally
claude`
Enter fullscreen mode
Exit fullscreen mode
Claude Code reads ANTHROPIC_BASE_URL automatically. No config files needed.
Use it with Python
import anthropic
client = anthropic.Anthropic( api_key="sl_your_key_here", base_url="https://api.simplylouie.com" )
message = client.messages.create( model="claude-opus-4-5", max_tokens=1024, messages=[{"role": "user", "content": "Hello, Claude"}] )
print(message.content)`
Enter fullscreen mode
Exit fullscreen mode
Use it with the JS/TS SDK
import Anthropic from '@anthropic-ai/sdk';
const client = new Anthropic({ apiKey: 'sl_your_key_here', baseURL: 'https://api.simplylouie.com', });
const message = await client.messages.create({ model: 'claude-opus-4-5', max_tokens: 1024, messages: [{ role: 'user', content: 'Hello' }], });
console.log(message.content);`
Enter fullscreen mode
Exit fullscreen mode
Use it with LangChain
from langchain_anthropic import ChatAnthropic
llm = ChatAnthropic( model="claude-opus-4-5", anthropic_api_key="sl_your_key_here", anthropic_api_url="https://api.simplylouie.com" )
response = llm.invoke("Explain async/await in one paragraph") print(response.content)`
Enter fullscreen mode
Exit fullscreen mode
Use it with LlamaIndex
from llama_index.llms.anthropic import Anthropic
llm = Anthropic( model="claude-opus-4-5", api_key="sl_your_key_here", base_url="https://api.simplylouie.com" )
response = llm.complete("Write a haiku about programming") print(response.text)`
Enter fullscreen mode
Exit fullscreen mode
What models are available?
All current Claude models:
-
claude-opus-4-5 — most capable
-
claude-sonnet-4-5 — balanced speed/quality
-
claude-haiku-3-5 — fastest, cheapest
How much does it cost?
$2/month flat rate.
No per-token billing. No usage meters. No surprise invoices.
For comparison:
-
Anthropic direct API: ~$15/million input tokens (Opus)
-
Claude Pro subscription: $20/month (only for claude.ai, not API)
-
SimplyLouie: $2/month for API access
If you're building something small, running experiments, or using Claude Code daily — flat rate saves you money.
The 7-day free trial
Get your API key at simplylouie.com/developers
Card required to start (standard SaaS), not charged for 7 days.
Why I built this
I was spending $20/month on Claude Pro just to get API access for Claude Code. Most of that quota sat unused.
Flat-rate makes more sense for developers who use Claude in bursts — heavy one week, light the next.
50% of revenue goes to animal rescue. That part wasn't required, it just felt right.
Drop your questions below — happy to help you get set up.
Sign in to highlight and annotate this article

Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
claudellamamodel
From Physics to Surrogate Intelligence: A Unified Electro-Thermo-Optimization Framework for TSV Networks
arXiv:2603.29268v1 Announce Type: new Abstract: High-density through-substrate vias (TSVs) enable 2.5D/3D heterogeneous integration but introduce significant signal-integrity and thermal-reliability challenges due to electrical coupling, insertion loss, and self-heating. Conventional full-wave finite-element method (FEM) simulations provide high accuracy but become computationally prohibitive for large design-space exploration. This work presents a scalable electro-thermal modeling and optimization framework that combines physics-informed analytical modeling, graph neural network (GNN) surrogates, and full-wave sign-off validation. A multi-conductor analytical model computes broadband S-parameters and effective anisotropic thermal conductivities of TSV arrays, achieving $5\%-10\%$ relative

M2H-MX: Multi-Task Dense Visual Perception for Real-Time Monocular Spatial Understanding
arXiv:2603.29236v1 Announce Type: new Abstract: Monocular cameras are attractive for robotic perception due to their low cost and ease of deployment, yet achieving reliable real-time spatial understanding from a single image stream remains challenging. While recent multi-task dense prediction models have improved per-pixel depth and semantic estimation, translating these advances into stable monocular mapping systems is still non-trivial. This paper presents M2H-MX, a real-time multi-task perception model for monocular spatial understanding. The model preserves multi-scale feature representations while introducing register-gated global context and controlled cross-task interaction in a lightweight decoder, enabling depth and semantic predictions to reinforce each other under strict latency

MemFactory: Unified Inference & Training Framework for Agent Memory
arXiv:2603.29493v1 Announce Type: new Abstract: Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged as a highly promising research direction. However, existing implementations remain highly fragmented and task-specific, lacking a unified infrastructure to streamline the integration, training, and evaluation of these complex pipelines. To address this gap, we present MemFactory, the first unified, highly modular training and inference framework specifically designed for memory-augmented agents. Inspired by the success of unified fine-tuning frameworks like LLaMA-Factory, MemFactory abstracts the memory lif
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Models
Tunisia: President accuses artificial intelligence of ‘conspiring’ against humans - Middle East Monitor
<a href="https://news.google.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?oc=5" target="_blank">Tunisia: President accuses artificial intelligence of ‘conspiring’ against humans</a> <font color="#6f6f6f">Middle East Monitor</font>

MemFactory: Unified Inference & Training Framework for Agent Memory
arXiv:2603.29493v1 Announce Type: new Abstract: Memory-augmented Large Language Models (LLMs) are essential for developing capable, long-term AI agents. Recently, applying Reinforcement Learning (RL) to optimize memory operations, such as extraction, updating, and retrieval, has emerged as a highly promising research direction. However, existing implementations remain highly fragmented and task-specific, lacking a unified infrastructure to streamline the integration, training, and evaluation of these complex pipelines. To address this gap, we present MemFactory, the first unified, highly modular training and inference framework specifically designed for memory-augmented agents. Inspired by the success of unified fine-tuning frameworks like LLaMA-Factory, MemFactory abstracts the memory lif

From Physics to Surrogate Intelligence: A Unified Electro-Thermo-Optimization Framework for TSV Networks
arXiv:2603.29268v1 Announce Type: new Abstract: High-density through-substrate vias (TSVs) enable 2.5D/3D heterogeneous integration but introduce significant signal-integrity and thermal-reliability challenges due to electrical coupling, insertion loss, and self-heating. Conventional full-wave finite-element method (FEM) simulations provide high accuracy but become computationally prohibitive for large design-space exploration. This work presents a scalable electro-thermal modeling and optimization framework that combines physics-informed analytical modeling, graph neural network (GNN) surrogates, and full-wave sign-off validation. A multi-conductor analytical model computes broadband S-parameters and effective anisotropic thermal conductivities of TSV arrays, achieving $5\%-10\%$ relative

Lie Generator Networks for Nonlinear Partial Differential Equations
arXiv:2603.29264v1 Announce Type: new Abstract: Linear dynamical systems are fully characterized by their eigenspectra, accessible directly from the generator of the dynamics. For nonlinear systems governed by partial differential equations, no equivalent theory exists. We introduce Lie Generator Network--Koopman (LGN-KM), a neural operator that lifts nonlinear dynamics into a linear latent space and learns the continuous-time Koopman generator ($L_k$) through a decomposition $L_k = S - D_k$, where $S$ is skew-symmetric representing conservative inter-modal coupling, and $D_k$ is a positive-definite diagonal encoding modal dissipation. This architectural decomposition enforces stability and enables interpretability through direct spectral access to the learned dynamics. On two-dimensional
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!