Help Center

Everything you need to get the most out of the 325 API.

🚀

Quick Start

Get your first API response in under 60 seconds

🔑

API Keys

Create, manage, and secure your API keys

📊

Playground

Test models interactively in your browser

💳

Pricing

Plans, credits, and subscription details

Frequently Asked Questions

How do I get started?

from openai import OpenAI
client = OpenAI(api_key="hm-YOUR_KEY", base_url="https://ai.empire325marketing.com/v1")
response = client.chat.completions.create(model="325-fast", messages=[{"role":"user","content":"Hello!"}])
print(response.choices[0].message.content)

Which model should I use?

325-fast — Simple tasks, HTML/CSS, shell scripts, SQL. 0.3s latency.
325-balanced — Code generation, math, reasoning, architecture. 2s latency.
325-ultra — Deep analysis, research, multi-step reasoning. 17s latency.
325-auto — Automatically routes to the best tier for your query.

How is this cheaper than OpenAI?

We use smart routing to send simple queries to fast/cheap models and complex queries to powerful models. This saves 91% on tokens compared to always using the most expensive model. Plus, our inference costs $0 — we pass the savings to you.

What models are available?

10+ frontier models: DeepSeek V4 Pro, Claude Opus 4.8, Claude Sonnet 4, Groq Llama 3.3, NVIDIA Nemotron 550B, Cerebras 120B, Kimi K2.6, GLM 5.2, MiniMax M3. Full catalog at /models.

Is my data stored?

We do NOT log prompt content, message history, or generated outputs. We only track token counts and request metadata for billing purposes. Read our Privacy Policy for details.

What payment methods do you accept?

All major credit/debit cards via Stripe. We offer monthly subscriptions ($9-99/mo) and one-time credit purchases. See Pricing.

How do I cancel?

Cancel anytime from your Settings page. Your API key remains active until the end of your billing period. No questions asked.