TimeTonic AI Offer: Public Cloud, Sovereign Private & Dedicated Server - The Complete Guide

From flexible cloud models to sovereign AI hosted in France - choose the right source for your data, your constraints and your budget.

Until now, TimeTonic offered a single way to integrate artificial intelligence into your automations: via major public cloud models. With this new release, TimeTonic moves from a single offering to three distinct AI modes, designed to cover every profile and every requirement: from the startup that wants access to the best models on the market, to the IT department of a hospital that cannot transfer its data outside France.

This complete guide explains how these three sources work, how to configure them, how to manage your credits, and how to get started quickly with ready-to-use templates.

AI at the Heart of TimeTonic Automations

In TimeTonic, artificial intelligence integrates directly into your automation scenarios, via a dedicated action: "Ask an AI". This action can be triggered automatically on any field change, document upload, or any condition you define.

What You Can Automate with AI

• Summarise a text or document
• Classify, translate or suggest a reply to a purchase request, customer email or support ticket
• Extract structured information from an invoice, contract or CV
• Analyse a document (PDF, image) via optical character recognition (OCR)
• Generate a personalised reply to an email
• Clean or reformat existing data

How an AI Action Works in a Workflow

1. A trigger occurs (field change, document upload, form submission, permalink clicked, input webhook)
2. A condition can be checked (non-empty field, file type, specific value)
3. The action "Ask an AI" is executed
4. The response is automatically saved into one or more fields in your workspace

Mode 1 - Public Cloud AI: Access the Best Models on the Market

Public cloud AI is the most accessible entry point. It gives direct access to the most powerful models available on the market from within TimeTonic, with no provider subscription required.

Available Models (OpenAI, Mistral, Anthropic...)

TimeTonic Credits or Personal API Key: When to Choose Which?

Public cloud AI offers two billing modes, switchable at any time:

Best for Which Use Cases?

Public cloud AI is recommended only if you need the most powerful models and don't have privacy or GDPR concerns. In most cases, the private & secure AI is recommended (see below).
Note also that if needed, you can mix both options with two consecutive automations: The first one with the Private & Secure AI to anonymise data and the second with the Public Cloud AI if you need more advanced reasoning.

Mode 2 - Private & Secure AI: Data Sovereignty, Hosted in France

This is the major new feature of this release for organisations with strict data protection requirements. Private and secure AI allows you to process your data using artificial intelligence models hosted in France, on TimeTonic's sovereign infrastructure.

Sovereign Hosting in France

The models used (Mistral, LLaMA, Qwen and other open source models) are deployed directly on TimeTonic's infrastructure in France. Your data never leaves this controlled environment. No transfer to an external provider or outside of France, no retentions, no training on your data, no exposure to third-party cloud API terms of use.

Zero Transfer to an External Provider

Unlike the public cloud AI option which routes your data to OpenAI, Mistral or Google servers, with TimeTonic's Private & Secure AI, your data never leaves our sovereign infrastructure in France — ISO 27001-certified, SOC 2-compliant, and built to the highest enterprise security standards. No exposure to external eyes. No data retention. No use for model training. Just full GDPR compliance, strict data residency within the European Union, and complete confidentiality.

And additional benefits, it will cost less, and will be better for the planet as it consumes much less electricity and water !

Available Models (Sovereign Infrastructure)

Best for Which Sectors?

Mode 3 - Dedicated AI Server: For Advanced Architectures

The third mode is aimed at organisations that already have an AI infrastructure, wish to deploy their own models or would like to benefit from a dedicated private server exclusively for their own use but still hosted on our sovereign infrastructure.

TimeTonic Hosting or Your Own Infrastructure

In both cases, no TimeTonic credits are consumed. Billing is entirely separate from your other AI sources. TimeTonic automatically detects the models available on your server during configuration.

Best for Which IT Profiles?

This mode is designed for CIOs and systems architects with specific requirements: proprietary or fine-tuned models, air-gap architectures, existing infrastructure to leverage, or performance and throughput constraints that shared solutions cannot meet. This is the maximum level of control.

OCR: Extract and Analyse Your PDFs and Images with AI

One of the most powerful AI features in TimeTonic is optical character recognition (OCR), available across all three sources. It enables automatic extraction of structured data from scanned documents.

What AI OCR Enables in TimeTonic

Concrete Use Cases

BYOK: Bring Your Own API Key

The BYOK (Bring Your Own Key) feature lets you use your own OpenAI or Mistral API key in your automations, replacing TimeTonic credits. It is available only with Option 1 Public Cloud AI

How It Works

In your "Ask an AI" action configuration (public cloud), enable the "Use my own API key" button, select your provider and enter your key. You then have access to your provider's full catalogue, including the most recent models (GPT-5, o3, o4, Ministral 3 14B, etc.). You can switch at any time between your personal key and TimeTonic credits, without losing your configuration.

Are Your Keys Stored by TimeTonic?

Yes, securely. Your API key is stored in the TimeTonic database in encrypted form. It can only be decrypted by the application itself and is never accessible in plain text, not even by the TimeTonic team. It is used solely to execute your AI actions within your automations, and is never shared or transmitted to third parties.

AI Credits: Understand, Track and Anticipate votre consommation

Credits Included by Plan

TimeTonic now offers the ability to use AI credits - with at least 2 million included in the PRO plan and 20 million included in the Business plan, at no additional cost

Tracking Your Usage in Real Time

Go to your Administration - Plan & Billing workspace to view the status of your two counters (private AI and public cloud AI). The gauges update in real time:

• 🟢 Green: less than 80% of quota consumed
• 🟠 Orange: 80% reached - a notification email is sent
• 🔴 Red: 100% reached - AI actions are suspended until monthly renewal

Automation logs allow you to analyse usage action by action: model used, input tokens, output tokens and total credits consumed. This is the ideal tool for comparing two models on the same task and choosing the most cost-effective one.

What Happens When Your Credits Run Out?

When the quota reaches 100%, AI automations are automatically suspended. Other automations (without AI calls) continue to function normally. Three options are available:

Choosing the Right AI Model selon votre usage

Selection Criteria

The model is the main lever on your credit consumption. Here is a quick selection guide:

Estimating Your Usage Before You Start

1. How large is what I am sending? A short email - ~300 credits, one page of text - ~500 credits, a 10-page contract - ~5,000 credits.
2. How long is the expected response? An extracted value - 5 to 20 credits, a response suggestion - ~100 credits, a structured summary - ~300 credits.
3. How many times will the scenario trigger per month? Multiply the cost per execution by the number of triggers.

AI Templates: Get Started in a Few Clicks

No need to start from scratch. TimeTonic offers a library of 10 ready-to-use AI templates, with pre-configured tables, structured fields and AI automations already set up.

Adapting a Template to Your Context

• AI source and model: select the source suited to your constraints and the model that fits your credit budget
• AI role and prompt: adjust the instructions to suit your sector and the expected level of precision
• Maximum token count: limit it if the response does not need to be long - this directly reduces your usage
• Response format and mapping: verify that the JSON properties exactly match the destination fields in your workspace

Conclusion: An AI Offer Designed for the Business Teams and the IT Department

With this triple offering, TimeTonic covers the full spectrum of enterprise AI needs: from the maximum flexibility of the public cloud to the total sovereignty of the dedicated server, via the security-accessibility balance of private AI hosted in France.

Adopted by the business teams. Validated by the IT department. And Vice Versa! Whatever your context - agile startup, growing SME, mid-sized company subject to sector obligations, or large group with a structured IT department - you will find in TimeTonic the unique combination of autonomy, flexility and ease of use needed by the business teams with the security, traceability and ease of integration required by the IT, that allows you and your teams to benefit - at last ! - from the full power of Artificial Intelligence to digitise and automate your processes, even the most advanced, without complexity and without putting your data and your company at risk.

Ready to get started? Explore the AI templates available in your TimeTonic space, test on a real use case and check the logs to fine-tune your configuration.