Skip to main content

AI Router product description

AI Router is a service for unified access to generative AI models from external providers without the need to deploy infrastructure. It allows you to work with available models through a single interface, centrally manage access keys and quotas, and receive consolidated reporting and analytics on their usage.

The terms of use for the AI Router product are defined by the Terms of Use for Individual Services: “AI Router” document and the SLA.

Use cases

  • connecting OpenAI, Anthropic, and other models using a single API key;
  • use a single code base for every OpenAI-compatible provider;
  • pay for models from a single balance instead of separate bills for each provider;
  • configuring budget limits;
  • monitor consumption via detailed, real-time analytics.

How it works

AI Router acts as a universal gateway between your application and external model providers. The service sends requests via an OpenAI-compatible API to the connected models, for more information, see the official OpenAI Developers documentation. You do not need to configure integrations with each provider separately — it is sufficient to use the AI Router API key in requests.

How to use AI Router

To access the service, complete registration and top up your balance with a minimum amount of 200 ₽.

To get started, create an AI Router; for more information, see the instructions in AI Router: Quick start.

After creating an AI Router, you can:

Available models

You can view the current list of models and pricing on selectel.ru, as well as after creating an AI router in the control panel: in the top menu, click Products → AI Router → AI router page → Models.

Areas of responsibility

Selectel provides

  • access to models via a public API compatible with the OpenAI API;
  • an AI router monitoring system in the control panel;
  • usage analytics;
  • the ability to manage limits for each AI router and API key;
  • technical support.

Selectel is not responsible for

  • the performance of requests made with API keys and request results;
  • the processing of personal data within the service;
  • integrating models into your projects;
  • the business logic of models in your projects.

Protecting API keys from compromise is your responsibility.

Pricing

AI Router is billed according to the pay-as-you-go model. Funds are deducted from the balance every hour for model consumption over the previous hour; for more details, see the instruction AI Router payment model and pricing.

What is included in the cost

Unlimited number of tokens for using available models.

Limitations

AI Router does not support:

  • the ability to train AI models;
  • uploading custom models to the catalog;
  • deploying models from the catalog on-premises, in A-DC, on dedicated servers, and in the certified cloud.