Open beta · v0.1

Every AI model,
one balance.

GPT, Claude, Gemini, FLUX, Suno — every frontier model in a single tab. Pay only for what you use. Plus agents that work in the background while you focus elsewhere.

One balance, every model
GPT, Claude, Gemini, FLUX, Suno
Passwordless sign-in
One-click secure access
Agents in the background
Research, monitoring, parsing

No subscriptions, no commitments — pay only for what you use

Available models
GPT-4o· OpenAIClaude Opus 4.7· AnthropicClaude Sonnet 4.6· AnthropicGemini 2.5 Pro· Googleo3-mini· OpenAIDALL·E 3· OpenAIFLUX 1.1· Black ForestSuno v4· Suno
Agents

Working while you're busy with something else.

Launch an agent — it watches, searches, drafts and replies in the background. Each run is debited from the same shared balance, with no separate subscriptions.

on demand

Research agent

Deep dive into a topic: searches, reads sources, distills the facts into a sourced report. Triggered by a single command.

researchauto
daily

Daily Digest

Every morning — a digest on your topics: news, releases, X and Telegram posts. Only what matters to you.

contentauto
24/7

Monitoring

Watches a price, brand mentions, page or API changes. Pings you the moment a trigger fires.

alertsauto
on schedule

Inbox triage

Sorts incoming mail, replies to routine messages, drafts answers for you. Connects to Gmail or IMAP.

emailauto
every PR

Code Review

Reads the diff in a PR, flags bugs, regressions and style issues. Connects to GitHub and GitLab.

engineeringauto
on schedule

Parser & analytics

Pulls data from sites and APIs, turns it into a table or dashboard, computes metrics, sends a summary.

dataauto
A custom agent for your task

Describe the task in plain words — we assemble an agent for it. No code, no workers, no separate infrastructure.

Launch your first agent
12
models
from 5 labs
context
on Claude Opus
<1.2с
first token
median latency
99.94%
uptime
last quarter
Live conversation

Speed and quality of the original.

We talk to the labs through their official APIs — no proxy farms with eight-second delays. Streaming token-by-token, just like ChatGPT.

streaming1M tokensvisionfiles
Claude Sonnet 4.6подключено
Features

Everything you need to work with AI.

Routing

One prompt — best model wins

Automatic model routing for each task. Simple questions go to a fast model, hard ones to the flagship.

Speed

First token in 1.2s

Direct channels to the labs' APIs. Median response time.

Geography

Servers in 3 regions

Frankfurt, Amsterdam, Helsinki. Closest one is auto-selected.

Batch processing

Upload PDFs, DOCX and images.

Attach up to 10 files, 50 MB total. O·LESA reads tables, images, and keeps the context across messages.

.pdf.docx.xlsx.png.jpg.csv.md.txt

Every model, one balance

GPT, Claude, Gemini, FLUX, Suno and more. Top up once — spend on any model without juggling subscriptions.

Passwordless sign-in

One secure click — no email, no password, no signup form. Your account is ready in 30 seconds.

Pay only for what you use

No subscriptions, no minimum charges, no monthly auto-renewals. Funds settle in 1–3 minutes.

No VPN required

Works from any IP. Our servers in Europe keep a direct line to every model.

Localized

Interface, support and docs in your language. Models reply in any language.

Privacy by default

Prompts are not retained by upstream providers. You can disable history or wipe your account in one click.

Billing

Pay per token, not per plan.

No subscriptions, no "300 requests per month" caps. Top up your balance — spend exactly what each call really costs at the upstream provider, in chat and in agents alike.

1
Step

Top up your balance

Several payment methods — no subscriptions, no auto-renewals. Funds settle in 1–3 minutes.

2
Step

Pay per token

Each model has a price per million tokens. You see it before the request and right after the response — in chat and in agents.

3
Step

Detailed usage

Spend by day, model, agent and individual request — in real time, no delay.

No subscriptions, no commitments. Unspent balance never expires.

FAQ

In case you're wondering.

How do I sign up?+

Sign-up takes 30 seconds — no email, no phone verification. One secure sign-in and you're in the chat. No forms.

What are agents and how do they work?+

An agent is an automated scenario that runs on a schedule or trigger: a daily news digest, a content monitor, a PR reviewer, an inbox responder. Each run is debited from your shared balance — no separate subscriptions or plans. Use ready-made agents from the catalog, or describe your task in plain words to assemble a custom one — no code.

Which models are available?+

GPT-4o, Claude Opus 4.7, Claude Sonnet 4.6, Gemini 2.5 Pro, FLUX 1.1 Pro and other frontier models. Full price list (per million input/output tokens) is publicly available on the Pricing page.

How does billing work?+

No subscriptions, no minimum monthly fee. Top up your balance — funds stay on your account and are spent on the fly: each model response and each agent run is debited at the provider's price. Unspent balance never expires.

How is this different from ChatGPT Plus?+

Every frontier model — GPT, Claude, Gemini, FLUX and others — is in a single tab, not just OpenAI. You don't need to maintain five subscriptions. Plus autonomous agents that work in the background.

Where can I see prices and usage?+

The full price list across every model (per million input/output tokens) is publicly available on the Pricing page, with a built-in calculator. Detailed usage by day, model, agent and individual request lives in your dashboard on the Usage page and updates in real time.

Do I need a VPN?+

No. The service works from any IP. All model traffic is routed through our European servers — no VPN, no foreign phone number.

Where are my conversations stored?+

In an encrypted database on servers in Germany. You can delete any conversation or your entire account at any time. No history is retained at upstream providers.

Open the chat in 30 seconds.

One click and you're in. No email, no signup form, no phone verification.

Try it free