Learnya in your tools and your applications.
An OpenAI-compatible API, keys with precise permissions, a command line and extensions for VS Code and JetBrains.
Your code, our models.
Keep the OpenAI SDK you already use, change the address and the key. The data stays in Switzerland.
- Completions, embeddings and images
- Streaming
- Same response formats
Three lines to change, not one more.
The URL, the key and the model. The rest of your code stays the same.
curl https://api.learnya.ai/v1/chat/completions \
-H "Authorization: Bearer $LEARNYA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "flash", "messages": [{"role": "user", "content": "Summarise this contract in five points."}]}'import os
from openai import OpenAI
client = OpenAI(base_url="https://api.learnya.ai/v1", api_key=os.environ["LEARNYA_API_KEY"])
r = client.chat.completions.create(
model="max",
messages=[{"role": "user", "content": "Summarise this contract in five points."}],
)
print(r.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({ baseURL: "https://api.learnya.ai/v1", apiKey: process.env.LEARNYA_API_KEY })
const r = await client.chat.completions.create({
model: "max",
messages: [{ role: "user", content: "Summarise this contract in five points." }],
})
console.log(r.choices[0].message.content)
Two models, one choice per call.
| Criterion | Learnya Flash | Learnya Max |
|---|---|---|
| For | Everyday work, quick answers | Long reasoning and complex tasks |
| Context | Long | Very long |
| API name | flash | max |
Developer tools.
OpenAI compatible
Completions, embeddings and images on api.learnya.ai, with the Flash and Max models.
Precise permissions
Scopes, rate limits, daily quotas and IP allowlists.
From the command line
The assistant in your terminal, with a local execution environment.
VS Code and JetBrains
Learnya works in your editor, on your code.
Learnya in your application in an hour.
A product team wants to add an assistant to its business software.
- 01
Key
An API key created with its permissions, quotas and allowed addresses.
- 02
Call
The OpenAI SDK you already use, pointed at api.learnya.ai.
- 03
Model
Flash for speed, Max for long reasoning, chosen per call.
- 04
Production
The data stays in Switzerland, and usage is tracked in the console.