1000 FAQs, 500 tutorials and explanatory videos. Here, there are only solutions!
Quick Start Guide: LLM API
LLM API is intended for developers who want to use Infomaniak's LLM (Large Language Model) in their applications.
What is LLM API?
LLM (Large Language Model) is a type of machine learning model that has been trained on a massive dataset of text and code. LLMs are capable of generating text, translating languages, writing various types of creative content, and providing informative answers to questions.
To stay true to its values, Infomaniak offers an LLM based on Mixtral, one of the most powerful open-source models available in the market, within the kSuite tools.
This sovereign artificial intelligence can, for example, assist you in writing, paraphrasing, or translating your emails.
LLM API allows you to connect your libraries or frameworks via API without an interface.
The API documentation can be found at https://developer.infomaniak.com/docs/api and contains information about available methods, parameters, and examples.
Obtaining LLM API
To use LLM API, it is necessary to create an API token.
Then, to access LLM API and, for example, check your daily consumption:
- Log in to the Infomaniak Manager (manager.infomaniak.com) from a web browser such as Brave or Firefox.
- Click on the icon at the top right of the interface (or navigate through the left sidebar menu, for example).
- Choose LLM API (in the Cloud Computing universe)
Only one product can exist per organization, but API tokens can be multiple.
LLM API can be used by the following users:
- Legal representative of the organization
- Administrators of the organization
- Organization collaborators with technical rights
Billing
- API billed by credit
- Each request consumes one LLM credit or token*
- Billing access is available to legal representatives and administrators
- Collaborators with technical rights have access to the documentation but not to the invoices
- A credit card is required to start using the API
- An unpaid invoice will result in the suspension of the service
- A spending limit can be set by a user with billing rights in the organization and on the product to limit unforeseen costs
- Pricing is presented on the LLM sales page
* LLM tokens (not to be confused with API tokens) are basic units used by language models to process and generate text. Each token typically represents a word, part of a word, or an entity in a corpus of text and is used for language learning and natural language generation.
Responsibilities
This language model generates text based on the data it has assimilated during its training, devoid of consciousness, intentions, or moral responsibilities. In case of inappropriate or dangerous use of this assistant, the responsibility lies with the user who takes these actions. It is crucial for the user to be aware that the information generated by the model is not always accurate and should not be considered a source of unquestionable information.
Users must exercise critical judgment and verify the information provided by the assistant from reliable sources when necessary. For example, if a person uses the model for crucial tasks such as medical, legal, or financial advice, they must take additional precautions to confirm the information from the model.