# How it works

## Credits

Credits are used to **interact with Obside** and **access its features**. Each interaction consumes a number of credits proportional to its complexity. This model makes pricing more **precise and aligned with actual usage**.

For example, a simple conversation with Obside Chat costs about **1 credit**, while creating or optimizing an agent consumes more. The more complex the task, the more credits are consumed.

You can check the exact cost of each interaction by opening the **message details** in Obside Chat (info icon).

***

## When are credits consumed?

The main types of operations that consume credits include:

* **Chat** — every message sent.
* **Agent creation** — the AI analyzes your description and generates the code.
* **Rephrasing and AI advice** — interpretation, suggestions, guardrails.
* **Backtest** — running a test on historical data.
* **Variations / AI optimization** — exploring parameter combinations.
* **AI agent analysis** — strengths, weaknesses, improvement angles.
* **Briefings and news queries** — news summaries and market reads.

The full credit history is accessible in **Settings → Usage & Billing**, with the breakdown by operation type.

***

## Renewal

Credits **reset every month** at your subscription's renewal date. They **don't roll over** from one month to the next (with the special case of yearly plans — see [Pricing](/misc/pricing.md)).

The **Free plan** has an initial credit allotment that isn't renewed monthly.

***

## Allocation per plan

Credits are included in each Obside subscription tier:

* **Free**: 100 credits
* **Core**: 1,000 credits / month (12,000 credits per year on the yearly plan)
* **Plus**: 2,000 credits / month (24,000 credits per year on the yearly plan)
* **Pro**: 4,000 credits / month (48,000 credits per year on the yearly plan)

For the full breakdown, see [Pricing](/misc/pricing.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.obside.com/credits/how-it-works.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.