Frequently Asked Questions
About the DeepGen platform
What is DeepGen?
DeepGen is a platform that lets businesses build a branded assistant — chatbot, voicebot and mailbot — tailored to their content and processes. Behind the scenes it gives you access to all the leading AI models (OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Meta and others), orchestrates them into workflows when needed, and exposes the result across chat, voice, email, Slack, Messenger and WhatsApp — under a single subscription.
What is a model?
A model in the context of generative AI, such as ChatGPT or Midjourney, is a computer program that has been trained on a large amount of data. This training allows the model to generate new content, like text or images, that is similar to the data it was trained on. The model uses machine learning algorithms to understand patterns in the data and then generate new content based on those patterns. The quality and capabilities of the generated content depend on the size and quality of the training data, as well as the sophistication of the machine learning algorithms used to create the model.
About customization
Can I get a custom assistant for my business?
Yes — that's the core of what we do. Give us your website URL and DeepGen turns your public pages into a knowledge base. In seconds, you get a working chatbot, voicebot and mailbot that answer questions about your business in your tone of voice. You can then brand it, restrict it to your domain, and add your own documents.
How fast can I get a chatbot for my site?
You get a working preview in seconds from a single URL. A production-ready assistant — branded, restricted to your domain, with human handoff and any additional data sources wired in — is typically live within one week.
Do the chatbot, voicebot and mailbot share the same knowledge base?
Yes. All three channels share the same knowledge, tone of voice, and human-handoff rules. Update the source once and every channel stays in sync.
What sources can I add beyond my website?
Today: your website URL plus any files you upload (PDFs, docs, spreadsheets). The assistant grounds its answers in those sources.
Can a human take over the conversation?
Yes — in a way that keeps the assistant useful by default. The bot stays in front of the conversation and handles what it can, but for sensitive or uncertain cases it can either ask a human to approve a draft reply, or route the question to a human and relay the answer back to the user. You decide which cases trigger which.
What are tokens and how to count them?
Tokens can be thought of as pieces of words. Before the API processes the prompts, the input is broken down into tokens. These tokens are not cut up exactly where the words start or end — tokens can include trailing spaces and even sub-words. Some rules of thumb:
- 1 token ≈ 4 chars in English
- 1 token ≈ ¾ words
- 100 tokens ≈ 75 words
- 1–2 sentences ≈ 30 tokens
- 1 paragraph ≈ 100 tokens
- 1,500 words ≈ 2048 tokens
For example, Wayne Gretzky's quote "You miss 100% of the shots you don't take" contains 11 tokens. The transcript of the US Declaration of Independence contains 1,695 tokens. How words are split into tokens is language-dependent — e.g. Cómo estás (Spanish for "How are you") contains 5 tokens for 10 chars. The higher token-to-char ratio can make it more expensive to implement the API for languages other than English.
What is a DeepGen Credit?
DeepGen credits are used to generate responses from our AI models. For instance, asking a question to a model like GPT-4o typically costs around 1 DeepGen credit. However, the exact cost can be significantly higher or lower depending on the specific model and the number of tokens used. To keep track of your credit usage, simply navigate to the Account menu on the Chat page, where you can monitor your credit balance.
Who is the developer of DeepGen?
DeepGen is developed by Deepiks, a French AI company incubated at Ecole Polytechnique.
How is support provided?
Support is provided exclusively by email at support@deepgen.app. Depending on the question, the answer is given by an AI within a few minutes or a human within 24 hours.
Billing & Pricing
What happens when I run out of credits?
If you reach your credit limit, you can either wait until your next billing cycle, upgrade to a higher plan, or buy additional credits.
Do credits roll over if I don't use them?
Credits reset at the beginning of each billing cycle and do not roll over. If you need more, you can upgrade your plan or purchase additional credits.
Can I change or cancel my plan at any time?
Yes, you can upgrade, downgrade, or cancel at any time from your account settings. Your changes will take effect in the next billing cycle.
Do you offer discounts for annual plans?
Yes — annual plans offer significant savings compared to monthly billing. You'll see the discount when selecting your plan.
What payment methods do you accept?
We accept all major credit cards and bank transfers. Enterprise customers can request invoicing.
About Deepiks
What is Deepiks?
Deepiks is the company developing the DeepGen platform.
Where is Deepiks located?
Deepiks is proudly located in Paris Saclay, at the heart of one of Europe's most vibrant and innovative technology and research ecosystems.
Mail address: Deepiks SAS, 21 Rue Jean Rostand, 91400 Orsay, France.
How can I contact Deepiks?
Support is provided exclusively by email at support@deepgen.app. For other questions, you can contact Deepiks by email at contact@deepgen.app, or call the Paris Office at +33 9 71 42 79 39.