> ## Documentation Index
> Fetch the complete documentation index at: https://docs.elumenta.ru/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Frequently asked questions about Elumenta API

## General

<AccordionGroup>
  <Accordion title="What is Elumenta API?">
    Elumenta API gives developers access to 52 AI models from 9 providers through a single REST API. Instead of managing separate accounts with OpenAI, Anthropic, Google, MidJourney, ElevenLabs and others — you get one endpoint, one token balance, and a unified response format.
  </Accordion>

  <Accordion title="Do I need separate accounts with OpenAI, Anthropic, etc.?">
    No. Elumenta handles all provider integrations. You only need an Elumenta account and API key.
  </Accordion>

  <Accordion title="Is Elumenta API compatible with OpenAI SDK?">
    Partially. The request format for text generation is OpenAI-compatible (same `messages` array format). However, the base URL and authentication header are different. See the [Quickstart](/en/quickstart) for details.
  </Accordion>
</AccordionGroup>

## Billing & Tokens

<AccordionGroup>
  <Accordion title="What is an Elumenta token?">
    Elumenta tokens are internal credits, not LLM context tokens. One Elumenta token represents a fixed compute budget. Each model has a fixed cost in Elumenta tokens per request. See the [Tokens](/en/concepts/tokens) page for the full pricing table.
  </Accordion>

  <Accordion title="Do unused subscription tokens roll over?">
    No. Subscription tokens reset each billing cycle. However, **token packages** (one-time purchases) never expire and carry over indefinitely.
  </Accordion>

  <Accordion title="What happens when I run out of tokens?">
    Requests return `402 Payment Required`. You can top up with a token package or upgrade your subscription from the [Dashboard](https://elumenta.ru/web/profile).
  </Accordion>

  <Accordion title="Can I use all models on the Starter plan?">
    The Starter plan gives you access to **Starter-tier models** (19 models) and 50 one-time tokens. All paid plans (Basic and above) unlock all 52 models. Plans differ only in monthly token allowance — not model access.
  </Accordion>
</AccordionGroup>

## Technical

<AccordionGroup>
  <Accordion title="How do I handle async generation (video, audio)?">
    Long-running generations return a generation ID immediately with `status: pending`. Poll `GET /api/v2/generate/{id}` until the status changes to `completed`. See the [Video Generation Guide](/en/guides/video-generation) for a full example.
  </Accordion>

  <Accordion title="What's the rate limit?">
    Rate limits depend on your plan. See the [Rate Limits](/en/concepts/rate-limits) page for details.
  </Accordion>

  <Accordion title="Can I use Elumenta from Russia?">
    Yes. Elumenta is designed for the Russian market. All AI provider calls are routed through a Cloudflare Workers proxy, so you don't need a VPN. Payments are accepted via Yookassa (Russian cards, SBP) and Telegram Stars.
  </Accordion>

  <Accordion title="Is there an SDK?">
    Official Python and JavaScript SDKs are in development. In the meantime, the API is standard REST — any HTTP client works. See the [SDKs](/en/resources/sdks) page.
  </Accordion>
</AccordionGroup>

## Models

<AccordionGroup>
  <Accordion title="How do I know which model to use?">
    Start with the [Models Catalog](/en/resources/models-catalog) for a full list with token costs. For most tasks: `gpt-5-nano` or `claude-haiku-4.5` for text (0 tkn), `dall-e-3` for images (5–13 tkn), `flux-1.1-pro` for photorealistic images (7 tkn), `kling-v2.1` for video (26–94 tkn).
  </Accordion>

  <Accordion title="How often are new models added?">
    New models are added as providers release them, typically within days of a major release. Check the [Changelog](/en/resources/changelog) for updates.
  </Accordion>

  <Accordion title="Does MidJourney work via API?">
    Yes. Elumenta uses the LegNext proxy to provide MidJourney access via API — no Discord bot required. Use `midjourney-v6` or `midjourney-turbo` for images, and `mj-video-480p` / `mj-video-720p` for videos.
  </Accordion>
</AccordionGroup>

## Support

<AccordionGroup>
  <Accordion title="How can I get help with the API?">
    We offer two support channels:

    **Telegram Support Bot** — For instant AI-powered help, visit [@ElumentaSupportBot](https://t.me/ElumentaSupportBot). Ask about features, billing, models, or technical issues and get answers in seconds. Available 24/7.

    **Email Support** — For billing questions, partnership inquiries, or detailed technical issues, contact [support@elumenta.ru](mailto:support@elumenta.ru). We typically respond within 24 hours (Mon–Fri, 10:00–19:00 MSK).
  </Accordion>
</AccordionGroup>

***