Eurylie
Our personal-assistant application. It uses the platform's conversation, document and memory features through its own app interface.
AI infrastructure and developer platform
1st AI Platform is the AI infrastructure and developer platform operated by 1StopTek. It provides AI processing on infrastructure we operate ourselves, through one versioned API. Eurylie, our personal assistant, is built on it.
Developer access is in testing
Overview
Eurylie is powered by the 1st AI Platform, with shared safety protections and centrally managed AI services.
Our personal-assistant application. It uses the platform's conversation, document and memory features through its own app interface.
A versioned HTTP API for your own products: chat completions, streaming, structured output, embeddings and usage, with project-scoped API keys.
Self-operated inference
Metadata-only metering
Limits you control
Use cases
Typical uses of the capabilities in testing today. They describe what the API supports, not finished customer deployments.
Answer questions and draft replies in your own interface, with your own system instructions.
Turn free text into JSON that matches your schema, validated before it reaches you.
Embed documents and queries to rank, group or route content.
Use AI where requests must not go to an external AI provider.
Website assistants
A website assistant answers your visitors' questions from your own website's content and suggests links to your pages. You set it up in the console in six guided steps and add one line of code to your website.
Example only: website assistants aren't available to customers yet.
Answers from your content
Only on your website
A spending limit first
Capabilities
Every capability is labelled with its current state. We only publish examples for endpoints that are implemented and tested.
| Capability | Status |
|---|---|
| Chat completions | In testing |
| Streaming | In testing |
| Structured output | In testing |
| Embeddings | In testing |
| Model discovery | In testing |
| Usage API | In testing |
| Document retrieval (RAG) | Planned |
| Tool and function calling | Planned |
| Image and audio input | Not supported |
Safety Layer
Pricing
Usage-based, per token: you pay for the input and output tokens your requests use. Testing stays free: nothing is charged until paid access opens and your organization accepts the paid terms.
Rate card rate-2026-11-12-r4
| Billing unit | Measured as | Price per 1M tokens |
|---|---|---|
| Chat input tokens | prompt tokens per request, same price for every model | €0.188 |
| Chat output tokens | completion tokens per request, same price for every model | €1.572 |
| Embedding input tokens | input tokens per request | Not included; priced separately |
| Requests | not billed separately | — |
| Document processing, storage | not offered on the Developer API | — |
Security, data processing and support
What we can state today, based on the implementation, and what is still being finalised.
Where it runs
No external model provider
Content
Services we use
Retention
Support and disclosure
Quick start, authentication, models, code samples, limits, errors and the API reference are in the Developers section.