Laguna Default
Our fast everyday model for drafting, extraction, summaries and chat.
Laguna-S-2.1
Per token$0.075 in, $0.16 out per 1M
Rental$0.71 / hour
Private AI
Sign in
Create a free account
Private AI services
Private AI for confidential work
AideaMaker's Private AI services are OpenAI-compatible AI models run by AideaMaker LLC. Choose your model from our approved list, change two lines of code, and pay per token or rent a model for yourself.
- Usage records only
- OpenAI-compatible
- Approved models
- Free sandbox key
Python
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.aideamaker.com/v1",
api_key=os.environ["AIDEAMAKER_API_KEY"],
)
reply = client.chat.completions.create(
model="Laguna-S-2.1",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)JavaScript
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.aideamaker.com/v1",
apiKey: process.env.AIDEAMAKER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "Laguna-S-2.1",
messages: [{ role: "user", content: "Hello" }],
});
console.log(reply.choices[0].message.content);curl
curl https://api.aideamaker.com/v1/chat/completions \
-H "Authorization: Bearer $AIDEAMAKER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "Laguna-S-2.1",
"messages": [{"role": "user", "content": "Hello"}]}'Privacy
We keep usage records only.
Your prompts and answers pass through our API gateway without being written to our databases, logs or backups. We keep usage records only (which key, which model, token counts, timing, result, and the calling address and software name) to bill, limit and run the service, for up to 400 days.
What we keep
- Which key and which model
- Token counts and timing
- The result of each call
- The calling address and software name
- Kept for up to 400 days, to bill, limit and run the service
Not written to our databases, logs or backups
- Your prompts
- The answers you receive
Software you build with us keeps only what its own page says it keeps.
Approved models
Choose your model from our approved list
Every key can call the models on the list. Name the one you want in each request.
Qwen3.8 Flash Next Quality
Our quality model for work that needs more careful reasoning.
quality
Per tokenComing soon
Rental$0.60 / hour
Two ways to pay
Pay per token, or rent a model for yourself
Prices in US dollars, published and the same for everyone.
Pay per token
$0.075/ 1M input tokensWhat one million tokens you send cost. A token is a short piece of a word; the usage counts in each response show how many your call used.
Laguna. Output $0.16 per 1M tokens.
- Prepaid credit from $5, no subscription
- Usage tiers raise your limits as you buy credit
- Calls stop when credit runs out: no surprise bills
Rent a model
$0.60/ hourThe price per hour of exclusive use. The term price beside it is this price times the hours of one term, paid in advance.
Qwen3.8 Flash Next, $432.00 for a 30-day term. Laguna $0.71 per hour, $511.20.
- Exclusive use of the model for your term
- One 30-day term, prepaid; every contract is approved first
- Validation takes up to 24 hours; your term starts when exclusive access is enabled
See rentals
1 contract availableHow many rental contracts can still be taken. One slot is shared by the models in the same configuration, and a request waiting for approval holds it until it is decided.
Start in minutes
Three steps to your first call
Create a free account
Verify your email and fill in your business profile.
Make a sandbox key
Try both models free, within the sandbox limits, or run a test in the playground.
Change two lines
Point your OpenAI SDK at this base URL and use your key. https://api.aideamaker.com/v1
FAQ
Questions about Private AI
What do you keep?
Usage records only: key, model, token counts, timing, result, and the calling address and software name, for up to 400 days. Your prompts and answers are not written to our databases, logs or backups.
Will it work with my code?
If you use Chat Completions with the OpenAI SDK, change the base URL and the key. Tools and JSON mode are not available yet; ask for JSON in your prompt.
Which models can I use?
The models on our approved list: Laguna and Qwen3.8 Flash Next today.
Why can a rental take up to 24 hours?
We check each contract before we enable exclusive access. You are not charged unless it is approved.
Try Private AI free
A sandbox key and the playground come with every free account.